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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sollten
    -0.07
     broth
    -0.07
     му
    -0.06
     sollte
    -0.06
     mob
    -0.06
     guns
    -0.06
     womb
    -0.06
     Chop
    -0.06
     splash
    -0.06
     Gam
    -0.06
    POSITIVE LOGITS
    ovah
    0.07
    ード
    0.07
     architectures
    0.07
    ichern
    0.06
     Autonomous
    0.06
    assertCount
    0.06
    ジオ
    0.06
    iden
    0.06
    UNE
    0.06
    WARD
    0.06
    Act Density 0.003%

    No Known Activations