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

    Neuronpedia

    INDEX
    Explanations

    safe

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    asting
    -0.07
    _in
    -0.07
     Chúng
    -0.06
    化
    -0.06
     tradition
    -0.06
    _named
    -0.06
     cycl
    -0.06
    indrical
    -0.06
    for
    -0.06
    Owned
    -0.06
    POSITIVE LOGITS
    (hdc
    0.07
     عالم
    0.07
    ınıf
    0.07
     mír
    0.06
    (',')↵
    0.06
    akhir
    0.06
     italiane
    0.06
    าป
    0.06
     się
    0.06
    *",
    0.06
    Act Density 8.138%

    No Known Activations