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

    Neuronpedia

    INDEX
    Explanations

    cables and wiring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Synopsis
    -0.07
     发
    -0.07
     피
    -0.06
    _review
    -0.06
     Tanzania
    -0.06
    amiliar
    -0.06
     clk
    -0.06
     freel
    -0.06
     candies
    -0.06
    留
    -0.05
    POSITIVE LOGITS
    Is
    0.07
     vardı
    0.07
    Are
    0.07
     '''
    0.06
     tenant
    0.06
     включа
    0.06
    (Me
    0.06
    ятий
    0.06
    EH
    0.06
    $name
    0.06
    Act Density 0.127%

    No Known Activations