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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enti
    -0.07
    GEN
    -0.07
    FR
    -0.07
    kil
    -0.07
    Produces
    -0.07
    stí
    -0.07
     Roles
    -0.07
    efe
    -0.06
    bit
    -0.06
    stile
    -0.06
    POSITIVE LOGITS
    학과
    0.07
    (lon
    0.07
     بوابة
    0.06
    \$
    0.06
    :',
    0.06
    ΟΙ
    0.06
    �
    0.06
    <Animator
    0.06
     Εξ
    0.06
     trục
    0.06
    Act Density 0.033%

    No Known Activations