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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .FirstName
    -0.08
    arth
    -0.07
     Sele
    -0.07
     Franti
    -0.07
     Globe
    -0.07
    .VISIBLE
    -0.06
    _hal
    -0.06
     intense
    -0.06
     langu
    -0.06
     urgency
    -0.06
    POSITIVE LOGITS
     dictionaryWith
    0.06
    	tv
    0.06
    .unpack
    0.06
     weird
    0.06
    ┴
    0.06
    |%
    0.06
     dick
    0.05
    ущ
    0.05
    .walk
    0.05
    HO
    0.05
    Act Density 0.000%

    No Known Activations