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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cting
    -1.13
    cted
    -0.75
    ctive
    -0.74
    AutoresizingMask
    -0.73
     ago
    -0.66
    tional
    -0.50
    躇
    -0.50
     portanto
    -0.49
     '\\;'
    -0.48
    ]")]
    -0.48
    POSITIVE LOGITS
     purpoſe
    0.72
     fubject
    0.67
     Conſ
    0.66
     laſt
    0.66
     Diſ
    0.62
    bidity
    0.61
     ſtate
    0.61
     cauſe
    0.60
     Conscience
    0.60
     reaſon
    0.60
    Act Density 0.073%

    No Known Activations