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

    Neuronpedia

    INDEX
    Explanations

    book prefaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reiben
    -0.07
    ّ
    -0.06
    gom
    -0.06
     Linkedin
    -0.06
    plate
    -0.06
    ưởng
    -0.06
    	animation
    -0.06
    极
    -0.06
    hyth
    -0.06
    řeba
    -0.06
    POSITIVE LOGITS
    .Parameters
    0.07
     multiple
    0.07
    TabIndex
    0.06
     elsewhere
    0.06
     augmented
    0.06
     продовж
    0.06
     Serv
    0.06
    _DT
    0.06
     xv
    0.06
     Μαρ
    0.06
    Act Density 0.025%

    No Known Activations