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

    Neuronpedia

    INDEX
    Explanations

    prob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (startTime
    -0.07
    ولة
    -0.07
     Cle
    -0.07
    avo
    -0.07
    ップ
    -0.07
     antidepress
    -0.07
     第一
    -0.07
     euler
    -0.07
    pace
    -0.06
    ansen
    -0.06
    POSITIVE LOGITS
    .Group
    0.06
    OMB
    0.06
     strive
    0.06
     bunların
    0.06
     divorced
    0.06
    tablename
    0.06
     APPLY
    0.06
    	std
    0.06
     Moderate
    0.06
    .fillStyle
    0.06
    Act Density 0.001%

    No Known Activations