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

    Neuronpedia

    INDEX
    Explanations

    to/within

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     punch
    -0.08
    _unlock
    -0.07
     infections
    -0.07
     Homepage
    -0.06
     career
    -0.06
     affirm
    -0.06
     pá
    -0.06
    _De
    -0.06
    Day
    -0.06
     logarith
    -0.06
    POSITIVE LOGITS
    �이
    0.06
    Associ
    0.06
    odox
    0.06
    laces
    0.06
    ैम
    0.06
    λμ
    0.06
    ainting
    0.06
    자
    0.06
     qx
    0.06
    expo
    0.06
    Act Density 0.004%

    No Known Activations