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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Abstract
    -0.07
    (answer
    -0.06
    ोकर
    -0.06
    真正
    -0.06
     Ecology
    -0.06
    Talk
    -0.06
     discovery
    -0.06
     vaccinated
    -0.06
     Talk
    -0.06
    攻击
    -0.06
    POSITIVE LOGITS
    -ended
    0.07
     brightness
    0.06
    _DB
    0.06
    eva
    0.06
     PCA
    0.06
    quito
    0.06
     Venezuelan
    0.06
     fw
    0.06
    rial
    0.06
     PCR
    0.06
    Act Density 0.087%

    No Known Activations