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

    Neuronpedia

    INDEX
    Explanations

    laboratory experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    walls
    -0.07
    _algorithm
    -0.07
     exon
    -0.07
     KDE
    -0.06
    结果
    -0.06
    सन
    -0.06
     住
    -0.06
    bbie
    -0.06
    資
    -0.06
     JR
    -0.06
    POSITIVE LOGITS
     Enhanced
    0.08
    ingle
    0.07
    .IsFalse
    0.07
    شناس
    0.06
    CONTENT
    0.06
     cung
    0.06
    .Simple
    0.06
     Bold
    0.06
     storyt
    0.06
     deterministic
    0.06
    Act Density 0.022%

    No Known Activations