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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ální
    -0.07
     k
    -0.07
    Its
    -0.06
    Reports
    -0.06
     reports
    -0.06
    ointments
    -0.06
    .Our
    -0.06
    Dating
    -0.06
    Auf
    -0.06
    Ag
    -0.06
    POSITIVE LOGITS
    同学
    0.07
    UNDLE
    0.06
     caster
    0.06
    Priv
    0.06
    ).*
    0.06
    TimeStamp
    0.06
    .Expression
    0.06
     uprising
    0.06
    ////////////////////////////////////////////////////
    0.06
    TIME
    0.06
    Act Density 0.000%

    No Known Activations