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

    Neuronpedia

    INDEX
    Explanations

    sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Php
    -0.07
    .MODE
    -0.07
     خلق
    -0.07
    еристи
    -0.06
     kissed
    -0.06
     změny
    -0.06
    รว
    -0.06
     ballot
    -0.06
    FSIZE
    -0.06
     rá
    -0.06
    POSITIVE LOGITS
    ("#{
    0.07
    ��
    0.07
     reversible
    0.06
    ################################################################
    0.06
    ươi
    0.06
    uates
    0.06
    default
    0.06
    trusted
    0.06
    เคร
    0.06
     방문
    0.06
    Act Density 0.002%

    No Known Activations