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

    Neuronpedia

    INDEX
    Explanations

    articles/prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ip
    -0.07
    ені
    -0.06
     HOLDER
    -0.06
     Amit
    -0.06
     Kam
    -0.06
    に
    -0.06
     Canyon
    -0.06
     Bd
    -0.06
    ACT
    -0.06
     plain
    -0.06
    POSITIVE LOGITS
    奴
    0.07
     mbedtls
    0.07
    returns
    0.07
     unidades
    0.06
     BPM
    0.06
    สร
    0.06
    emas
    0.06
    Pk
    0.06
     classifier
    0.06
    λικ
    0.06
    Act Density 0.030%

    No Known Activations