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

    Neuronpedia

    INDEX
    Explanations

    People's names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tilt
    -0.07
     Ramos
    -0.07
     maps
    -0.06
     philosophy
    -0.06
    agus
    -0.06
    KeyEvent
    -0.06
    "At
    -0.06
     Coinbase
    -0.06
     tuple
    -0.05
     bomber
    -0.05
    POSITIVE LOGITS
     Pods
    0.07
    结
    0.07
    _LOG
    0.07
    _ENCODE
    0.07
    чик
    0.07
    ----------</
    0.07
    가능
    0.07
    髪
    0.07
     '"';↵
    0.07
    카라
    0.07
    Act Density 0.012%

    No Known Activations