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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usu
    -0.07
     görün
    -0.07
    ItemClick
    -0.06
    sus
    -0.06
    {_
    -0.06
    톡
    -0.06
    kla
    -0.06
     материал
    -0.06
    eyJ
    -0.06
    LOSS
    -0.06
    POSITIVE LOGITS
    	audio
    0.08
     laws
    0.07
     north
    0.07
    τρ
    0.07
     sparked
    0.06
    Additional
    0.06
    FRING
    0.06
    車
    0.06
    APA
    0.06
    (Configuration
    0.06
    Act Density 0.017%

    No Known Activations