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

    Neuronpedia

    INDEX
    Explanations

    Figure references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sociales
    -0.07
    炎
    -0.07
    	msg
    -0.06
    034
    -0.06
    regular
    -0.06
     spreads
    -0.06
    eload
    -0.06
     Division
    -0.06
    	error
    -0.06
    전
    -0.06
    POSITIVE LOGITS
    .hy
    0.07
    \Action
    0.06
    out
    0.06
    ABA
    0.06
    outing
    0.06
     hukuk
    0.06
    .bill
    0.06
     prostě
    0.06
     oppon
    0.06
    _FLOW
    0.06
    Act Density 0.002%

    No Known Activations