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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ece
    0.99
    ం
    0.98
     enthalpy
    0.96
     tangente
    0.96
    ௦
    0.93
    traj
    0.92
    endente
    0.92
     πολ
    0.92
    aue
    0.92
     Nonlinear
    0.91
    POSITIVE LOGITS
    ')(
    0.77
    غت
    0.74
    Scenic
    0.73
     incidentally
    0.73
    Sounds
    0.72
    Wood
    0.72
    च
    0.70
    ('*
    0.69
    Style
    0.68
    कर्ताओं
    0.68
    Act Density 0.006%

    No Known Activations