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

    Neuronpedia

    INDEX
    Explanations

    ph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loss
    -0.07
    奖
    -0.06
     drilled
    -0.06
    _equals
    -0.06
    -layer
    -0.06
     UUID
    -0.06
     zám
    -0.06
     luckily
    -0.06
     장
    -0.06
     Lucas
    -0.06
    POSITIVE LOGITS
     Astr
    0.07
     http
    0.07
    LOGY
    0.07
    ascar
    0.07
    har
    0.07
     OCI
    0.06
    displayText
    0.06
    spi
    0.06
     spre
    0.06
    над
    0.06
    Act Density 0.003%

    No Known Activations