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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unavoidable
    -0.07
    ान
    -0.06
    wid
    -0.06
    otes
    -0.06
    uded
    -0.06
     blasting
    -0.06
    	column
    -0.06
    řad
    -0.06
    社会
    -0.06
    逸
    -0.06
    POSITIVE LOGITS
    Driving
    0.07
     Arm
    0.06
    ikipedia
    0.06
     iniciar
    0.06
     موقع
    0.06
    _:*
    0.06
    .return
    0.06
     Malone
    0.06
    」を
    0.06
     Fairfield
    0.06
    Act Density 0.029%

    No Known Activations