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

    Neuronpedia

    INDEX
    Explanations

    analyzing or changing values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ש
    0.44
    irsi
    0.42
    istic
    0.42
    ur
    0.42
     Blind
    0.41
    urr
    0.41
    itic
    0.40
     Florent
    0.40
     다음과
    0.40
     bb
    0.40
    POSITIVE LOGITS
     první
    0.44
    ەیە
    0.44
    DUCT
    0.42
     chahiye
    0.42
     embankment
    0.42
     effecting
    0.42
     există
    0.42
     ayudarte
    0.41
     ghat
    0.41
     nhẹ
    0.40
    Act Density 0.000%

    No Known Activations