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

    Neuronpedia

    INDEX
    Explanations

    embedding documents and media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    440
    -0.07
    (bus
    -0.07
    Capability
    -0.07
     puck
    -0.06
    951
    -0.06
     walking
    -0.06
    Clinton
    -0.06
    540
    -0.06
     college
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .Can
    0.07
     texte
    0.06
     방법
    0.06
     Geile
    0.06
     BOOLEAN
    0.06
    위를
    0.06
     перет
    0.06
    .Lo
    0.06
    TYPO
    0.05
     getElement
    0.05
    Act Density 0.067%

    No Known Activations