Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    indicators of research findings and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Research study results and findings

    np_acts-logits-general · gemini-2.0-flash

    research findings and implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {{/
    -0.71
    WithMany
    -0.67
    UnsafeEnabled
    -0.66
     raconte
    -0.58
    databinding
    -0.56
     sanno
    -0.55
    プリング
    -0.54
    httphttps
    -0.53
     Administrativna
    -0.52
    Vidite
    -0.52
    POSITIVE LOGITS
     future
    0.84
     Future
    0.71
    出版年
    0.71
    Future
    0.68
    future
    0.67
    valuable
    0.66
     implications
    0.64
    Implications
    0.63
    今後の
    0.61
     valuable
    0.59
    Act Density 1.540%

    No Known Activations