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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     procur
    -0.07
     sub
    -0.06
    Pdf
    -0.06
     unicorn
    -0.06
     falsely
    -0.06
    Fu
    -0.06
     tyto
    -0.06
    (g
    -0.06
    eným
    -0.06
     Marr
    -0.06
    POSITIVE LOGITS
     });↵↵
    0.06
     Accept
    0.06
    .Msg
    0.06
    */,↵
    0.06
     располаг
    0.06
    lookup
    0.06
    )get
    0.06
     JJ
    0.06
     **/↵↵
    0.06
     reopening
    0.06
    Act Density 0.005%

    No Known Activations