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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enamel
    -0.07
    -path
    -0.07
    	not
    -0.07
    _teacher
    -0.07
    toast
    -0.07
    SetFont
    -0.07
    mam
    -0.07
    shade
    -0.06
     Tat
    -0.06
    ıt
    -0.06
    POSITIVE LOGITS
     Barb
    0.06
    海外
    0.06
    ffff
    0.06
     unfavorable
    0.06
    ENABLE
    0.06
    ंड
    0.06
    Latitude
    0.06
     immutable
    0.05
    ries
    0.05
     Emmanuel
    0.05
    Act Density 0.562%

    No Known Activations