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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Est
    -0.07
    dığı
    -0.07
    Arrow
    -0.06
    essen
    -0.06
     repealed
    -0.06
    )v
    -0.06
    _TOOL
    -0.06
     spoil
    -0.06
    flight
    -0.06
    nv
    -0.06
    POSITIVE LOGITS
     Each
    0.07
    Each
    0.07
    Selected
    0.07
     glaring
    0.06
    (Layout
    0.06
     cruz
    0.06
     Regiment
    0.06
    .Generate
    0.06
     Immediate
    0.06
    .gif
    0.06
    Act Density 0.351%

    No Known Activations