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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     logo
    -0.08
    公报
    -0.07
    ülü
    -0.07
    .synthetic
    -0.07
    莽
    -0.07
    _COPY
    -0.07
     Signing
    -0.07
     ál
    -0.07
     näch
    -0.07
    �
    -0.06
    POSITIVE LOGITS
    נית
    0.08
    (ST
    0.07
     strains
    0.07
    Sales
    0.07
    fecha
    0.07
    sched
    0.07
    햊
    0.06
    ಪ
    0.06
    oters
    0.06
     mannen
    0.06
    Act Density 0.001%

    No Known Activations