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

    Neuronpedia

    INDEX
    Explanations

    900

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .JPanel
    -0.07
    ']},↵
    -0.07
    vé
    -0.06
     공격
    -0.06
     Soc
    -0.06
    ))↵↵
    -0.06
    vj
    -0.06
     �
    -0.06
    uč
    -0.06
    ){
↵
    -0.06
    POSITIVE LOGITS
     seznam
    0.07
    clidean
    0.07
     animated
    0.06
    nameof
    0.06
    animated
    0.06
    frequency
    0.06
     experimentation
    0.06
     wreckage
    0.06
    asyon
    0.06
     ryb
    0.06
    Act Density 0.000%

    No Known Activations