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

    Neuronpedia

    INDEX
    Explanations

    real data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     đơn
    0.52
     accesso
    0.52
     amis
    0.51
    ಬ್ಬಿಣ
    0.50
     ağı
    0.49
     igualmente
    0.49
     cliquer
    0.48
    cü
    0.48
     conceito
    0.47
     imagem
    0.47
    POSITIVE LOGITS
    phones
    0.52
    javaHome
    0.49
    ipp
    0.48
    nuxt
    0.48
    java
    0.48
    uals
    0.47
    خير
    0.47
    ಣಿ
    0.47
    zab
    0.46
    ?
    0.46
    Act Density 0.000%

    No Known Activations