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

    Neuronpedia

    INDEX
    Explanations

    expert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pest
    -0.07
     industrial
    -0.06
    	hash
    -0.06
     берег
    -0.06
    Indexed
    -0.06
    codegen
    -0.06
     버
    -0.06
     Ideas
    -0.06
     incentives
    -0.06
    /host
    -0.06
    POSITIVE LOGITS
     вмі
    0.07
     Magic
    0.07
     mastery
    0.07
    feat
    0.07
     swiftly
    0.06
    Skill
    0.06
     الرياض
    0.06
    _SOC
    0.06
    ‌گ
    0.06
     skill
    0.06
    Act Density 0.006%

    No Known Activations