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

    Neuronpedia

    INDEX
    Explanations

    terms related to gyroscopic effects and stabilization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hygroscopic, gyroscopic, giraffe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SPC
    -0.44
    Bem
    -0.37
     Nox
    -0.35
    bong
    -0.35
     urmă
    -0.35
     Amé
    -0.35
     Baf
    -0.35
    microsoft
    -0.35
     Exter
    -0.34
    ANCO
    -0.34
    POSITIVE LOGITS
     gyro
    1.56
     Gyro
    1.49
    Gyro
    1.39
    gyro
    1.32
    roscope
    1.02
     giro
    0.82
     Giro
    0.82
    giro
    0.80
     gy
    0.76
    Giro
    0.76
    Act Density 0.008%

    No Known Activations