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

    Neuronpedia

    INDEX
    Explanations

    toward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    チェ
    -0.07
     september
    -0.06
     Changed
    -0.06
    OSE
    -0.06
    atters
    -0.06
    crime
    -0.06
     statistically
    -0.06
    -filled
    -0.06
    %p
    -0.06
    'y
    -0.06
    POSITIVE LOGITS
    yw
    0.07
     vůči
    0.07
    .SimpleButton
    0.06
     timber
    0.06
    _%
    0.06
     zprav
    0.06
     Cisco
    0.06
    ρίς
    0.06
     SSL
    0.06
     naše
    0.06
    Act Density 0.024%

    No Known Activations