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

    Neuronpedia

    INDEX
    Explanations

    shows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '{@
    -0.07
    ощи
    -0.06
     ISR
    -0.06
     vene
    -0.06
    //--------------------------------------------------------------↵
    -0.06
     "]"
    -0.06
    _positive
    -0.06
    amework
    -0.06
     मण
    -0.06
     xrange
    -0.05
    POSITIVE LOGITS
     مورد
    0.07
    _Address
    0.07
    maries
    0.07
    at
    0.07
    mercial
    0.07
    ์ซ
    0.06
    urchase
    0.06
     magical
    0.06
    .M
    0.06
     invoice
    0.06
    Act Density 0.000%

    No Known Activations