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

    Neuronpedia

    INDEX
    Explanations

    unicode character

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Regular
    -0.09
    (gs
    -0.09
     beslist
    -0.08
     લે
    -0.08
    (ax
    -0.08
     dü
    -0.08
    (response
    -0.08
    Best
    -0.08
     regular
    -0.08
     clown
    -0.08
    POSITIVE LOGITS
    切
    0.08
    ాశ
    0.08
    0.07
     ಶಾಸ
    0.07
    ակ
    0.07
    ోట
    0.07
    �
    0.07
    �
    0.07
    .saved
    0.07
    okat
    0.07
    Act Density 0.001%
    No Known Activations