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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     úkol
    -0.07
     Demp
    -0.07
    topl
    -0.06
     QB
    -0.06
     wer
    -0.06
     WaitForSeconds
    -0.06
     qu
    -0.06
     националь
    -0.06
     mayor
    -0.06
    brıs
    -0.06
    POSITIVE LOGITS
    =image
    0.07
     imageName
    0.06
    HANDLE
    0.06
    从
    0.06
    	des
    0.06
    cg
    0.06
    _"+
    0.06
    εφ
    0.06
     接
    0.06
    _slave
    0.06
    Act Density 0.033%

    No Known Activations