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

    Neuronpedia

    INDEX
    Explanations

    passwords or random strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CEL
    -0.07
    _beg
    -0.07
     third
    -0.07
    	packet
    -0.07
     파일첨부
    -0.07
     abundant
    -0.07
     pray
    -0.07
    _pres
    -0.07
     Ellen
    -0.06
     drop
    -0.06
    POSITIVE LOGITS
    к
    0.07
     qx
    0.06
    fp
    0.06
    _HIDE
    0.06
     bv
    0.06
    №№
    0.06
    ฝ
    0.06
    	at
    0.06
     řed
    0.06
     mne
    0.06
    Act Density 0.051%

    No Known Activations