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

    Neuronpedia

    INDEX
    Explanations

    have be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    нима
    -0.07
    edriver
    -0.07
     Nap
    -0.06
     blackColor
    -0.06
     bậc
    -0.06
    -cli
    -0.06
    Mb
    -0.06
     Eag
    -0.06
     bureau
    -0.06
    BYTES
    -0.06
    POSITIVE LOGITS
     стен
    0.07
     внутри
    0.07
    )]↵
    0.06
    _ABS
    0.06
    이지
    0.06
     เด
    0.06
    elah
    0.06
     lact
    0.06
     newName
    0.06
     masa
    0.06
    Act Density 0.014%

    No Known Activations