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

    Neuronpedia

    INDEX
    Explanations

    Dividing assets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ldap
    -0.07
     migrants
    -0.07
     CLR
    -0.07
     Protocol
    -0.07
     KM
    -0.06
    Cs
    -0.06
     Schools
    -0.06
     grazing
    -0.06
    Tables
    -0.06
    Languages
    -0.06
    POSITIVE LOGITS
     Remix
    0.07
     surre
    0.07
    铫
    0.07
     responsiveness
    0.07
    sink
    0.06
    .sess
    0.06
    ハイ
    0.06
    pré
    0.06
    꾐
    0.06
    _logic
    0.06
    Act Density 0.013%

    No Known Activations