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

    Neuronpedia

    INDEX
    Explanations

    court

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sin
    -0.07
    iệc
    -0.06
     unequiv
    -0.06
    FW
    -0.06
     произош
    -0.06
     sang
    -0.06
    CHA
    -0.06
     dương
    -0.06
     sinful
    -0.06
     Jesus
    -0.06
    POSITIVE LOGITS
     �
    0.08
     Mai
    0.07
    _PERIOD
    0.07
    counts
    0.06
     نمود
    0.06
    _mirror
    0.06
     ό
    0.06
    -remove
    0.06
    ký
    0.06
    روج
    0.06
    Act Density 0.005%

    No Known Activations