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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mesa
    -0.08
     متح
    -0.07
    jni
    -0.07
    addin
    -0.06
     Fairy
    -0.06
    ktop
    -0.06
    لى
    -0.06
    Xem
    -0.06
    acing
    -0.06
    .dao
    -0.06
    POSITIVE LOGITS
     ступ
    0.08
     insight
    0.07
     Российской
    0.06
    (line
    0.06
     create
    0.06
    permalink
    0.06
    "><?
    0.06
    	scope
    0.06
    rganization
    0.06
    义
    0.06
    Act Density 0.005%

    No Known Activations