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

    Neuronpedia

    INDEX
    Explanations

    octal, membership, follow, dollars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    punkt
    0.93
    ا
    0.91
    èrement
    0.84
    y
    0.84
    u
    0.84
    ۔
    0.83
    enswert
    0.81
    :
    0.81
    면
    0.79
    LNG
    0.78
    POSITIVE LOGITS
     holomorphic
    0.96
     configuring
    0.89
    هو
    0.88
     torsional
    0.87
     ainfi
    0.86
    зец
    0.86
     экспо
    0.85
     circularly
    0.84
    configuring
    0.80
    ιον
    0.79
    Act Density 0.000%

    No Known Activations