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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _playing
    -0.07
     tua
    -0.07
    _MANAGER
    -0.07
     referenced
    -0.06
    aits
    -0.06
    Calculate
    -0.06
     Ori
    -0.06
     ingr
    -0.06
    ogs
    -0.06
     akadem
    -0.06
    POSITIVE LOGITS
    현
    0.06
     Eph
    0.06
    现
    0.06
     setOpen
    0.06
     мет
    0.06
    ®,
    0.06
    768
    0.06
     Kid
    0.06
    显
    0.06
    保
    0.06
    Act Density 0.002%

    No Known Activations