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

    Neuronpedia

    INDEX
    Explanations

    taylor, corvus, liquidity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     educación
    0.80
     Educación
    0.79
     Punta
    0.77
     Esta
    0.77
     denuncia
    0.75
     Baja
    0.74
     Pursuit
    0.72
     Bost
    0.71
     identific
    0.70
     promet
    0.70
    POSITIVE LOGITS
    дар
    0.86
    groupBox
    0.86
    tay
    0.81
    enumValues
    0.81
    Taylor
    0.80
    نون
    0.80
    た
    0.78
    muş
    0.77
    もの
    0.77
    ável
    0.77
    Act Density 0.000%

    No Known Activations