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

    Neuronpedia

    INDEX
    Explanations

    exercise, body posture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     livelihoods
    -0.08
     Berkeley
    -0.08
     количе
    -0.08
    quantity
    -0.08
    金额
    -0.08
     Toolkit
    -0.08
     consumes
    -0.08
    patch
    -0.07
    utek
    -0.07
     tickets
    -0.07
    POSITIVE LOGITS
     പുല
    0.09
    保持
    0.09
     പറ
    0.08
    avoz
    0.08
     പാല
    0.08
     유지
    0.08
     राख
    0.08
    ീസ
    0.08
    �
    0.08
    /bl
    0.08
    Act Density 0.004%

    No Known Activations