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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uttar
    -0.08
    俾
    -0.07
    巡视
    -0.07
    вали
    -0.07
    本领
    -0.07
    椿
    -0.07
    菟
    -0.07
    erah
    -0.07
    IRS
    -0.07
    condition
    -0.07
    POSITIVE LOGITS
    .Page
    0.07
    萣
    0.07
    _NET
    0.07
     Assoc
    0.07
    _quad
    0.07
     repo
    0.07
    Assoc
    0.06
    _rsp
    0.06
    _imgs
    0.06
    支出
    0.06
    Act Density 0.001%

    No Known Activations