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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    附
    -0.07
     IDictionary
    -0.07
     Evans
    -0.07
     Kum
    -0.07
     representations
    -0.07
     minds
    -0.07
    კ
    -0.06
    Э
    -0.06
    ไอ
    -0.06
    接著
    -0.06
    POSITIVE LOGITS
    RESSED
    0.08
    głos
    0.08
    weekday
    0.07
    .junit
    0.07
    passes
    0.07
    _wave
    0.07
    olta
    0.07
    䓫
    0.06
    buff
    0.06
     טיול
    0.06
    Act Density 0.003%

    No Known Activations