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

    Neuronpedia

    INDEX
    Explanations

    Code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Modes
    -0.07
    $instance
    -0.07
    Administr
    -0.07
     commentator
    -0.07
    .downcase
    -0.07
     bekommen
    -0.06
    	common
    -0.06
     accur
    -0.06
     GestureDetector
    -0.06
    mmc
    -0.06
    POSITIVE LOGITS
    ✷
    0.07
    ۦ
    0.07
    Extended
    0.07
    claims
    0.07
    许
    0.07
    バイク
    0.06
    (sentence
    0.06
    (lua
    0.06
     paw
    0.06
    树叶
    0.06
    Act Density 0.245%

    No Known Activations