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

    Neuronpedia

    INDEX
    Explanations

    enabled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     právě
    -0.07
     tons
    -0.07
    warz
    -0.06
     trg
    -0.06
    bm
    -0.06
     그는
    -0.06
     depressive
    -0.06
     Tarih
    -0.06
     zeigen
    -0.06
    nerRadius
    -0.06
    POSITIVE LOGITS
     )↵
    0.08
     [
    0.07
    .hibernate
    0.07
    .isSuccess
    0.07
    ě
    0.07
     )
↵
    0.06
    ěl
    0.06
     ]);↵
    0.06
     Relationships
    0.06
    ;'↵
    0.06
    Act Density 0.003%

    No Known Activations