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

    Neuronpedia

    INDEX
    Explanations

    methodology or approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    υ
    0.49
    ص
    0.45
    </
    0.45
     ktoré
    0.44
     samochod
    0.44
    _
    0.44
     którzy
    0.44
    ?
    0.44
     supernovae
    0.43
     நிறைந்த
    0.43
    POSITIVE LOGITS
    ું
    0.53
    dV
    0.51
    casa
    0.48
    cV
    0.47
    ление
    0.47
    쨰
    0.47
    cata
    0.46
    И
    0.46
    از
    0.45
    вим
    0.45
    Act Density 1.526%

    No Known Activations