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

    Neuronpedia

    INDEX
    Explanations

    conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kit
    -0.08
     sık
    -0.07
     aluno
    -0.07
     Flood
    -0.06
     thuê
    -0.06
    投資
    -0.06
     Cher
    -0.06
    _SAFE
    -0.06
     화
    -0.06
    مة
    -0.06
    POSITIVE LOGITS
    +'"
    0.06
     к
    0.06
     omega
    0.06
     volunt
    0.06
     handc
    0.06
     parach
    0.06
    にて
    0.06
     xamarin
    0.06
    бут
    0.06
     Extend
    0.06
    Act Density 0.010%

    No Known Activations