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

    Neuronpedia

    INDEX
    Explanations

    daily

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    一头
    -0.09
    ਮ
    -0.07
    egr
    -0.07
    鸫
    -0.07
    egal
    -0.07
    ()."
    -0.07
    .BOLD
    -0.07
    “They
    -0.07
    trägt
    -0.06
    偭
    -0.06
    POSITIVE LOGITS
     Hö
    0.07
     الحكوم
    0.07
    _emb
    0.07
     najczę
    0.07
     randomized
    0.06
     меня
    0.06
     perchè
    0.06
    _mark
    0.06
     Chamber
    0.06
     Sanders
    0.06
    Act Density 0.003%

    No Known Activations