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

    Neuronpedia

    INDEX
    Explanations

    fed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ísk
    -0.07
    ieron
    -0.07
    олай
    -0.07
    олее
    -0.06
     onu
    -0.06
    _epsilon
    -0.06
     dáng
    -0.06
    어서
    -0.06
    reat
    -0.06
     adrenaline
    -0.06
    POSITIVE LOGITS
     fed
    0.09
    -fed
    0.07
     ever
    0.07
    fed
    0.07
    كت
    0.06
     Ned
    0.06
     smoking
    0.06
    UF
    0.06
     rpm
    0.06
     PRESS
    0.06
    Act Density 0.003%

    No Known Activations