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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hton
    -0.07
    .ml
    -0.07
    .М
    -0.06
     Quick
    -0.06
    �
    -0.06
    ruption
    -0.06
     уд
    -0.06
    _DAYS
    -0.06
    DK
    -0.06
    .getActive
    -0.06
    POSITIVE LOGITS
    sensor
    0.07
     worker
    0.06
    sav
    0.06
     servicio
    0.06
    اه
    0.06
     defined
    0.06
     walmart
    0.06
     Allow
    0.06
     Респ
    0.06
    	operator
    0.06
    Act Density 0.000%

    No Known Activations