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

    Neuronpedia

    INDEX
    Explanations

    project management/specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _THIS
    -0.08
     atal
    -0.07
     nyuma
    -0.07
     Provincia
    -0.07
    经理
    -0.07
    wechsl
    -0.07
     κύ
    -0.07
    ىرى
    -0.07
     Segu
    -0.07
    oooo
    -0.07
    POSITIVE LOGITS
     plus
    0.08
    -ath
    0.08
     देखकर
    0.08
    所得
    0.08
    .x
    0.08
     aerob
    0.07
     alapján
    0.07
    script
    0.07
     tadi
    0.07
    -hearted
    0.07
    Act Density 0.122%

    No Known Activations