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

    Neuronpedia

    INDEX
    Explanations

    programming related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tipped
    -0.06
     Payne
    -0.06
     condemn
    -0.06
     caric
    -0.06
    อท
    -0.06
    Phi
    -0.06
    _cc
    -0.06
    Visual
    -0.06
     Phen
    -0.06
    cedures
    -0.06
    POSITIVE LOGITS
     berg
    0.08
     skirm
    0.07
    .changed
    0.06
    emma
    0.06
     Gotham
    0.06
    (feed
    0.06
    _friend
    0.06
    enis
    0.06
     onslaught
    0.06
    som
    0.06
    Act Density 0.065%

    No Known Activations