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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    visit
    -0.07
    	comment
    -0.07
     반
    -0.07
    尚
    -0.07
    /event
    -0.06
     lombok
    -0.06
    Objects
    -0.06
    -this
    -0.06
    рез
    -0.06
    誰
    -0.06
    POSITIVE LOGITS
     automotive
    0.07
     satellites
    0.06
     basically
    0.06
    ammad
    0.06
     μον
    0.06
    NET
    0.06
     ظرف
    0.06
     ducks
    0.06
     Vinyl
    0.06
     cellphone
    0.06
    Act Density 0.045%

    No Known Activations