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

    Neuronpedia

    INDEX
    Explanations

    programming code and languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     altru
    -0.09
    ודה
    -0.08
     Alonso
    -0.08
    790
    -0.07
    வை
    -0.07
    necessarily
    -0.07
    ுமே
    -0.07
    ایل
    -0.07
    ogado
    -0.07
     evangelical
    -0.07
    POSITIVE LOGITS
    erialized
    0.08
    gere
    0.07
     Ua
    0.07
     Radio
    0.07
     schedule
    0.07
     terlebih
    0.07
     Iter
    0.07
     Hu
    0.07
     array
    0.07
     ਸਰ
    0.07
    Act Density 0.098%

    No Known Activations