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

    Neuronpedia

    INDEX
    Explanations

    polearms, polemics, poleis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ALITY
    0.45
    ality
    0.41
    itatea
    0.40
     সানডে
    0.40
    र्पण
    0.40
    riteria
    0.39
    ik
    0.38
    iyam
    0.37
    alities
    0.37
    իկ
    0.36
    POSITIVE LOGITS
    mic
    0.64
    Mic
    0.60
     mic
    0.57
    mica
    0.57
     pamphlet
    0.57
     micros
    0.56
    mical
    0.54
     Mic
    0.53
     MIC
    0.53
    Michel
    0.53
    Act Density 0.001%

    No Known Activations