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

    Neuronpedia

    INDEX
    Explanations

    code, math, symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hledem
    -0.06
    lection
    -0.06
     performer
    -0.06
     diagon
    -0.06
     next
    -0.06
     go
    -0.05
    영
    -0.05
    rb
    -0.05
    фік
    -0.05
     cin
    -0.05
    POSITIVE LOGITS
    」，
    0.07
     stalo
    0.07
    ("""
    0.07
     Mold
    0.07
    FREE
    0.07
    _PENDING
    0.07
     Sha
    0.06
     '__
    0.06
     '<?
    0.06
    /'.
    0.06
    Act Density 0.177%

    No Known Activations