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

    Neuronpedia

    INDEX
    Explanations

    API code and mentions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Answer
    -0.07
     Modes
    -0.06
    办法
    -0.06
     situation
    -0.06
     Replies
    -0.06
     Applications
    -0.06
    𝐄
    -0.06
    :ss
    -0.06
    يين
    -0.06
    -Z
    -0.06
    POSITIVE LOGITS
     Thom
    0.08
     ------
    0.07
    倓
    0.07
    вел
    0.06
     directional
    0.06
    .Local
    0.06
     Seah
    0.06
    ḵ
    0.06
    .Merge
    0.06
    清淡
    0.06
    Act Density 0.031%

    No Known Activations