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

    Neuronpedia

    INDEX
    Explanations

    say 1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scripts
    -0.08
    _CLIP
    -0.07
    (Content
    -0.07
     Meet
    -0.07
    Trace
    -0.07
     Customs
    -0.07
    deviceId
    -0.07
     Ethnic
    -0.07
    投放
    -0.07
     über
    -0.06
    POSITIVE LOGITS
    فال
    0.08
    Haunted
    0.07
    ह
    0.07
    新华社
    0.07
    ච
    0.07
    你会
    0.06
    accounts
    0.06
    hexdigest
    0.06
     echoing
    0.06
    筻
    0.06
    Act Density 0.001%

    No Known Activations