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

    Neuronpedia

    INDEX
    Explanations

    foreign language titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fashion
    0.53
    ka
    0.52
    ke
    0.50
    kor
    0.48
    functional
    0.47
    کو
    0.46
    flexible
    0.46
    ile
    0.46
    forth
    0.46
    formats
    0.45
    POSITIVE LOGITS
     Korean
    0.47
     በአ
    0.46
     Italian
    0.45
    u
    0.44
     ho
    0.42
     Italien
    0.42
     IRR
    0.42
     Paraná
    0.42
     Serbian
    0.42
     moo
    0.41
    Act Density 0.000%

    No Known Activations