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

    Neuronpedia

    INDEX
    Explanations

    HIV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Utils
    -0.08
    ideal
    -0.07
    _geometry
    -0.07
     Nicholas
    -0.07
    恨
    -0.07
    (Tag
    -0.07
    Perhaps
    -0.07
    Added
    -0.07
    haus
    -0.07
    /assert
    -0.07
    POSITIVE LOGITS
     hmot
    0.06
     genes
    0.06
    INATION
    0.06
        ↵    ↵
    0.05
     stroll
    0.05
    нез
    0.05
     داو
    0.05
     eos
    0.05
     nigeria
    0.05
    �
    0.05
    Act Density 0.949%

    No Known Activations