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

    Neuronpedia

    INDEX
    Explanations

    first number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generals
    0.40
     whore
    0.38
     famed
    0.38
     অন্যদের
    0.38
     stepped
    0.38
    他の
    0.36
     hands
    0.36
     footsteps
    0.36
     furent
    0.36
    alop
    0.35
    POSITIVE LOGITS
     번째
    0.68
    번째
    0.55
    されていない
    0.35
     والنصف
    0.35
     legnagyobb
    0.34
     Participating
    0.33
    INTRESOURCE
    0.33
    이자
    0.33
    Component
    0.33
    component
    0.33
    Act Density 0.020%

    No Known Activations