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

    Neuronpedia

    INDEX
    Explanations

    study and research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τς
    -0.07
    finalize
    -0.07
    spe
    -0.07
     crystall
    -0.06
     seinen
    -0.06
     camouflage
    -0.06
    _FIXED
    -0.06
    iae
    -0.06
     concatenated
    -0.06
    _SCHED
    -0.06
    POSITIVE LOGITS
    urahan
    0.06
    antaged
    0.06
    _chi
    0.06
    特色
    0.06
    loses
    0.06
    .method
    0.05
     […]↵
    0.05
    |)↵
    0.05
    lod
    0.05
     encountering
    0.05
    Act Density 0.128%

    No Known Activations