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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     věn
    -0.07
     Sche
    -0.07
     feet
    -0.06
     Ν
    -0.06
     draped
    -0.06
    них
    -0.06
    _leave
    -0.06
    criteria
    -0.06
    warning
    -0.06
     siding
    -0.06
    POSITIVE LOGITS
    =lambda
    0.07
    ]['
    0.07
    :The
    0.07
    	al
    0.06
    edback
    0.06
     복
    0.06
    Prot
    0.06
    >\
    0.06
    :`
    0.06
    �
    0.06
    Act Density 0.106%

    No Known Activations