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

    Neuronpedia

    INDEX
    Explanations

    shift or transition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.95
    nsp
    1.75
    nz
    1.74
     santé
    1.71
    nv
    1.70
    ु
    1.65
    th
    1.64
    nl
    1.64
    ný
    1.63
    nte
    1.63
    POSITIVE LOGITS
     đổi
    1.93
     seamlessly
    1.73
    𝗮
    1.70
    tokens
    1.59
    ität
    1.57
     Shifts
    1.48
     వచ్చిన
    1.45
     volna
    1.44
     Chameleon
    1.44
    رى
    1.42
    Act Density 0.412%

    No Known Activations