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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dent
    -0.07
     ty
    -0.07
    ik
    -0.07
    스테
    -0.07
    四
    -0.07
    Gap
    -0.06
    IK
    -0.06
    咨询
    -0.06
     differentiation
    -0.06
     lateral
    -0.06
    POSITIVE LOGITS
    .SelectSingleNode
    0.06
     дозвол
    0.06
    rollers
    0.06
    _FLAGS
    0.06
     absurd
    0.06
    .layer
    0.06
     вида
    0.06
    avatars
    0.06
    .Clone
    0.06
    fabs
    0.06
    Act Density 0.164%

    No Known Activations