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

    Neuronpedia

    INDEX
    Explanations

    push

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ot
    -0.07
    demo
    -0.07
     نموده
    -0.07
     발
    -0.06
    cot
    -0.06
    ظˆ
    -0.06
     };↵↵↵
    -0.06
     fulfil
    -0.06
    有
    -0.06
     heals
    -0.06
    POSITIVE LOGITS
    essaging
    0.07
    .I
    0.07
     tasked
    0.06
    orsi
    0.06
     safety
    0.06
     entrenched
    0.06
     والتي
    0.06
     getPlayer
    0.06
    —I
    0.06
     ге
    0.06
    Act Density 0.005%

    No Known Activations