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

    Neuronpedia

    INDEX
    Explanations

    code repositories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hop
    -0.07
    _ary
    -0.06
    eceği
    -0.06
     Than
    -0.06
     ushort
    -0.06
    HU
    -0.06
    458
    -0.06
     ball
    -0.06
     Dit
    -0.06
    utschen
    -0.06
    POSITIVE LOGITS
     MIME
    0.07
     고객
    0.07
    _pieces
    0.06
     Calculates
    0.06
    (vertical
    0.06
     shim
    0.06
    PAGE
    0.06
    ocard
    0.06
    àn
    0.06
     lax
    0.06
    Act Density 0.014%

    No Known Activations