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

    Neuronpedia

    INDEX
    Explanations

    regular

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DEN
    -0.07
     verw
    -0.07
     sind
    -0.06
    fds
    -0.06
    (Program
    -0.06
     FAQ
    -0.06
    .events
    -0.06
     bois
    -0.06
    '),↵↵
    -0.06
     Traditional
    -0.06
    POSITIVE LOGITS
    zz
    0.07
     언어
    0.07
    failed
    0.06
     Güvenlik
    0.06
    활동
    0.06
     چشم
    0.06
     astronom
    0.06
    ηγ
    0.06
    archical
    0.06
    _equals
    0.06
    Act Density 0.014%

    No Known Activations