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

    Neuronpedia

    INDEX
    Explanations

    references to errors or issues in coding and tech-related contexts

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

    Japanese words followed by particles

    np_acts-logits-general · gemini-2.0-flash

    intention, possibility, meaning, hope, existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.53
    ,
    -0.48
    ing
    -0.44
     
    -0.43
     to
    -0.43
    /
    -0.40
    ējās
    -0.39
     the
    -0.38
     further
    -0.38
     favor
    -0.38
    POSITIVE LOGITS
    Personensuche
    0.95
    tvguidetime
    0.89
     تانيه
    0.85
     يتيمه
    0.84
     gynhyrchwyd
    0.83
     avoient
    0.83
    abestanden
    0.82
     nakalista
    0.81
    OGND
    0.81
     démocr
    0.80
    Act Density 0.050%

    No Known Activations