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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spectators
    -0.07
     Copper
    -0.06
    hou
    -0.06
     burnt
    -0.06
     contacting
    -0.06
     Corp
    -0.06
     rang
    -0.06
    _fore
    -0.06
     Crus
    -0.06
     dir
    -0.06
    POSITIVE LOGITS
    573
    0.06
    |#
    0.06
    -di
    0.06
    ano
    0.06
    USER
    0.06
    _AES
    0.06
    /input
    0.06
     thuis
    0.06
    adoop
    0.06
    دا
    0.06
    Act Density 0.000%

    No Known Activations