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

    Neuronpedia

    INDEX
    Explanations

    seguint

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HO
    -0.06
     displacement
    -0.06
    皮
    -0.06
     Barbie
    -0.06
    CAN
    -0.06
    _cycle
    -0.06
    Coverage
    -0.06
     Clifford
    -0.06
    .circular
    -0.06
    -abortion
    -0.06
    POSITIVE LOGITS
    aviours
    0.07
     велик
    0.07
     relent
    0.07
    ossed
    0.07
    FirstOrDefault
    0.07
     coworkers
    0.07
     (![
    0.07
     hiển
    0.06
     backButton
    0.06
     jedin
    0.06
    Act Density 0.007%

    No Known Activations