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

    Neuronpedia

    INDEX
    Explanations

    important

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imprison
    -0.07
     Lonely
    -0.07
    煨
    -0.07
     Similarly
    -0.07
     configuring
    -0.07
    aron
    -0.07
    可用于
    -0.07
     meaning
    -0.07
    ило
    -0.07
    𫘬
    -0.07
    POSITIVE LOGITS
     "{
    0.07
    cite
    0.07
    ocht
    0.06
     agents
    0.06
     Sand
    0.06
    开封
    0.06
     entra
    0.06
     tous
    0.06
    achers
    0.06
     Works
    0.06
    Act Density 0.079%

    No Known Activations