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

    Neuronpedia

    INDEX
    Explanations

    Enabling eager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一款
    -0.85
     Chandigarh
    -0.79
    幢
    -0.76
    mitt
    -0.75
    Logged
    -0.74
     réactions
    -0.74
    onej
    -0.73
     yeah
    -0.73
    ına
    -0.72
    FZ
    -0.72
    POSITIVE LOGITS
     Minnesota
    1.02
    xla
    0.95
     Prairie
    0.95
     tensorflow
    0.92
    KeyType
    0.91
     ops
    0.88
     pylint
    0.84
     Minneapolis
    0.84
    }}_
    0.84
     soát
    0.83
    Act Density 0.045%

    No Known Activations