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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anja
    -0.07
    .diff
    -0.07
     Terrorism
    -0.07
    ähr
    -0.07
     mill
    -0.07
    partner
    -0.07
    .Orientation
    -0.07
     Coff
    -0.06
    aternion
    -0.06
    Cab
    -0.06
    POSITIVE LOGITS
     `-
    0.06
     miêu
    0.06
     Playing
    0.06
    kur
    0.06
    _FRAMEBUFFER
    0.05
    ाँ
    0.05
     probs
    0.05
     inhabit
    0.05
     lived
    0.05
     Tunnel
    0.05
    Act Density 0.005%

    No Known Activations