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

    Neuronpedia

    INDEX
    Explanations

    code snippets and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -driving
    -0.09
    outputs
    -0.08
    ordat
    -0.08
     direita
    -0.08
    �
    -0.08
    wär
    -0.08
     contam
    -0.08
     eventuell
    -0.08
     Eduardo
    -0.07
     applaud
    -0.07
    POSITIVE LOGITS
    用于
    0.12
     используется
    0.10
     versatile
    0.10
     použí
    0.09
    万能
    0.09
     применяется
    0.09
     предназнач
    0.09
     함수
    0.09
     bruges
    0.09
     funciona
    0.08
    Act Density 0.024%

    No Known Activations