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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     morally
    -0.08
     depuis
    -0.07
     보여
    -0.07
    useRal
    -0.07
    <Address
    -0.07
    HA
    -0.06
    omedical
    -0.06
     Default
    -0.06
    -Ta
    -0.06
    Mb
    -0.06
    POSITIVE LOGITS
     KEEP
    0.06
    oldur
    0.06
    anos
    0.06
     tying
    0.06
    йн
    0.06
     گذ
    0.05
     Hamas
    0.05
    陷
    0.05
    SGlobal
    0.05
    (wp
    0.05
    Act Density 0.028%

    No Known Activations