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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    따
    -0.07
     Saga
    -0.07
    cors
    -0.06
     beled
    -0.06
    Creature
    -0.06
    rescia
    -0.06
    アニメ
    -0.06
     energia
    -0.06
    Poly
    -0.06
    amburger
    -0.06
    POSITIVE LOGITS
    .Bunifu
    0.07
     indoors
    0.07
    TypeName
    0.07
    。不过
    0.07
    ->{_
    0.07
    <boost
    0.06
    .Ultra
    0.06
    [N
    0.06
    ूम
    0.06
     никогда
    0.06
    Act Density 0.013%

    No Known Activations