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

    Neuronpedia

    INDEX
    Explanations

    terms related to experimental and analytical methodologies in scientific contexts

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

    on the basis of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perchè
    -0.59
     Amongst
    -0.57
     dimana
    -0.53
     diatas
    -0.53
     amongst
    -0.52
     idag
    -0.52
     disini
    -0.51
     poichè
    -0.51
    UnusedPrivate
    -0.49
     didalam
    -0.48
    POSITIVE LOGITS
     stället
    0.65
     Afterward
    0.60
     enggak
    0.56
    Ϫ
    0.54
     nont
    0.54
    ⫹
    0.52
     ‘‘
    0.52
    さまざま
    0.52
     ;
    0.52
    enzial
    0.51
    Act Density 0.380%

    No Known Activations