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

    Neuronpedia

    INDEX
    Explanations

    UI elements and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    THREAD
    -0.07
    moil
    -0.07
    registro
    -0.07
     �
    -0.06
     discouraged
    -0.06
    /")↵
    -0.06
     Disco
    -0.06
     पद
    -0.06
    _absolute
    -0.06
     електрон
    -0.06
    POSITIVE LOGITS
     packets
    0.07
    _tA
    0.07
     endanger
    0.07
     tert
    0.07
    _EXEC
    0.06
     HOLD
    0.06
    _HOT
    0.06
    _Do
    0.06
     sensors
    0.06
    ñ
    0.06
    Act Density 0.144%

    No Known Activations