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

    Neuronpedia

    INDEX
    Explanations

    specific verbs and actions related to information disclosure and processes

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

    action verbs followed by direct objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TestBed
    -0.41
     also
    -0.35
     olyan
    -0.33
     followed
    -0.32
    awtextra
    -0.32
    addGap
    -0.32
    Especies
    -0.31
     parede
    -0.31
     FOLLOW
    -0.31
    titudine
    -0.31
    POSITIVE LOGITS
    󠁣
    0.70
    UrlResolution
    0.59
     виправивши
    0.57
    postsleuth
    0.57
    makeText
    0.57
    IUrlHelper
    0.57
    Panamoan
    0.54
    keyColumn
    0.53
    хьтан
    0.53
     transfieras
    0.52
    Act Density 0.082%

    No Known Activations