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

    Neuronpedia

    INDEX
    Explanations

    Philosophical/Existential musings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     impression
    -0.07
    eway
    -0.07
    泥
    -0.06
     Snap
    -0.06
    도록
    -0.06
     Services
    -0.06
     inspired
    -0.06
     folks
    -0.06
    獲
    -0.06
     connect
    -0.06
    POSITIVE LOGITS
     Begins
    0.07
    FormGroup
    0.07
    λαν
    0.06
    UNC
    0.06
     уча
    0.06
    भग
    0.06
    _TER
    0.06
    acje
    0.06
     ActivatedRoute
    0.06
    罗斯
    0.06
    Act Density 0.158%

    No Known Activations