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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FINE
    -0.07
    Inserted
    -0.07
    TextArea
    -0.07
     arreglo
    -0.07
     kilomet
    -0.06
    Bindable
    -0.06
    _emlrt
    -0.06
    Verbose
    -0.06
    tığı
    -0.06
    annel
    -0.06
    POSITIVE LOGITS
    幫助
    0.09
    (helper
    0.07
     overwhelm
    0.07
     cust
    0.07
    仓
    0.07
    帮助
    0.07
    ・
    0.07
     protecting
    0.07
    宠爱
    0.07
    超越
    0.07
    Act Density 0.071%

    No Known Activations