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

    Neuronpedia

    INDEX
    Explanations

    scared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Diss
    -0.06
     Emerson
    -0.06
    คาส
    -0.06
    .square
    -0.06
     vase
    -0.06
    .getFont
    -0.06
     overflowing
    -0.06
     невозможно
    -0.06
     beams
    -0.06
    favor
    -0.06
    POSITIVE LOGITS
     Comcast
    0.07
     activ
    0.07
     frightening
    0.07
    .nt
    0.07
    342
    0.07
    .int
    0.07
     idols
    0.07
    Although
    0.06
     terrifying
    0.06
    ogr
    0.06
    Act Density 0.022%

    No Known Activations