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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فيها
    -0.07
     dst
    -0.07
    ็นท
    -0.07
     furry
    -0.07
    Value
    -0.07
    ugi
    -0.07
     TASK
    -0.07
    图
    -0.06
    ยว
    -0.06
    Content
    -0.06
    POSITIVE LOGITS
    Proof
    0.06
     CrossRef
    0.06
    -MM
    0.06
     commerc
    0.06
     detainees
    0.06
    ocumented
    0.06
    _US
    0.06
    locking
    0.06
    -INFRINGEMENT
    0.05
    {%
    0.05
    Act Density 0.021%

    No Known Activations