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

    Neuronpedia

    INDEX
    Explanations

    code and concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conjugated
    0.62
    μές
    0.56
     Conjug
    0.56
     નું
    0.54
     магни
    0.54
     Ou
    0.53
     voltou
    0.53
     וע
    0.53
     قم
    0.53
     Всего
    0.52
    POSITIVE LOGITS
     sobbing
    0.68
    comedy
    0.67
    ⌋
    0.67
    一块
    0.64
    bbing
    0.63
    continued
    0.62
    fitting
    0.61
    lessly
    0.60
    clad
    0.60
     piani
    0.60
    Act Density 0.000%

    No Known Activations