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

    Neuronpedia

    INDEX
    Explanations

    techniques explained through steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     దాని
    0.47
    ᄈ
    0.47
    ِي
    0.46
     U
    0.45
     its
    0.44
    ់
    0.43
     Arithmetic
    0.43
     ល
    0.43
    的花
    0.43
    lett
    0.43
    POSITIVE LOGITS
     қай
    0.44
     इंजन
    0.44
     unstoppable
    0.44
     opérateur
    0.44
    点は
    0.43
    determine
    0.43
     Vivek
    0.43
     acidic
    0.42
     خالد
    0.41
     jugu
    0.41
    Act Density 0.004%

    No Known Activations