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

    Neuronpedia

    INDEX
    Explanations

    ##

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    duction
    -0.07
     which
    -0.07
     melody
    -0.06
    wap
    -0.06
    Align
    -0.06
    drv
    -0.06
    _draw
    -0.06
     koje
    -0.06
    boost
    -0.06
    Creators
    -0.06
    POSITIVE LOGITS
    ##
    0.07
     disposal
    0.07
    ####
    0.06
     Από
    0.06
    ออนไลน
    0.06
    ###
    0.06
    )...
    0.06
     귀
    0.06
     Однако
    0.06
     abusive
    0.06
    Act Density 0.006%

    No Known Activations