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

    Neuronpedia

    INDEX
    Explanations

    patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    song
    -0.07
     Names
    -0.07
     acid
    -0.07
     real
    -0.07
     Sự
    -0.07
    ###
    -0.07
    _s
    -0.07
    -log
    -0.07
    绿色
    -0.07
    確定
    -0.07
    POSITIVE LOGITS
    Epoch
    0.07
    黼
    0.07
    Optimizer
    0.06
     laten
    0.06
     società
    0.06
    ど
    0.06
    Alert
    0.06
    ㇻ
    0.06
    muştur
    0.06
    יפול
    0.06
    Act Density 0.004%

    No Known Activations