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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    活
    -0.07
    呼
    -0.06
    matching
    -0.06
     }}}
    -0.06
     nive
    -0.06
     (\<
    -0.06
    ietf
    -0.06
    PagerAdapter
    -0.06
    pickup
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Victims
    0.07
    _STEP
    0.06
     رسول
    0.06
     TOD
    0.06
     PAR
    0.06
    想到
    0.06
     Heidi
    0.06
     تقد
    0.06
     OM
    0.06
     formas
    0.06
    Act Density 0.025%

    No Known Activations