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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ้าต
    -0.07
    ्र
    -0.07
    öy
    -0.07
     rats
    -0.06
    rw
    -0.06
    亞
    -0.06
    ｉ
    -0.06
    億
    -0.06
     oi
    -0.06
    ali
    -0.06
    POSITIVE LOGITS
     верес
    0.07
    _ENDPOINT
    0.07
     misleading
    0.07
    责
    0.06
     appet
    0.06
    	buff
    0.06
     bill
    0.06
     inversion
    0.06
    .deserialize
    0.06
    ,pos
    0.06
    Act Density 0.030%

    No Known Activations