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

    Neuronpedia

    INDEX
    Explanations

    options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     educated
    -0.07
    _tokens
    -0.06
    _calendar
    -0.06
     Guarantee
    -0.06
    _observer
    -0.06
    scaling
    -0.06
     NBC
    -0.06
     Joint
    -0.06
     seja
    -0.06
    	cur
    -0.06
    POSITIVE LOGITS
     إذ
    0.07
    ,height
    0.06
     fill
    0.06
    isia
    0.06
    ká
    0.06
     IndexError
    0.06
     Sho
    0.06
     miss
    0.06
    )":
    0.06
    ,message
    0.06
    Act Density 0.051%

    No Known Activations