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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roz
    -0.07
     Pipe
    -0.07
    iloc
    -0.07
     quizzes
    -0.06
    /sample
    -0.06
    cams
    -0.06
    ivent
    -0.06
    ays
    -0.06
     coma
    -0.06
     MutableList
    -0.06
    POSITIVE LOGITS
    EMPLATE
    0.06
    एक
    0.06
    Opera
    0.06
    aincontri
    0.06
     NSURL
    0.05
     αυτή
    0.05
    كه
    0.05
    emplates
    0.05
    THIS
    0.05
    透
    0.05
    Act Density 0.025%

    No Known Activations