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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PST
    -0.07
    Intl
    -0.06
    .sim
    -0.06
     XCT
    -0.06
    sında
    -0.06
    ptal
    -0.06
    _POST
    -0.06
    .instance
    -0.06
    bugs
    -0.06
     isa
    -0.06
    POSITIVE LOGITS
     аналіз
    0.07
     "[%
    0.06
     vaguely
    0.06
    .factory
    0.06
    Jwt
    0.06
    Yellow
    0.06
    );">↵
    0.06
    AXB
    0.06
    ového
    0.06
     starving
    0.06
    Act Density 0.000%

    No Known Activations