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

    Neuronpedia

    INDEX
    Explanations

    199

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /dir
    -0.07
    	step
    -0.06
    :item
    -0.06
    kop
    -0.06
     KC
    -0.06
     هد
    -0.06
     glGet
    -0.06
    COVER
    -0.06
    乘
    -0.06
    @Component
    -0.05
    POSITIVE LOGITS
    (xi
    0.07
     Rome
    0.06
     Typ
    0.06
     fla
    0.06
     guesses
    0.06
    ï
    0.06
    Sing
    0.06
     GenerationType
    0.06
     matrimon
    0.06
    _special
    0.06
    Act Density 0.001%

    No Known Activations