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

    Neuronpedia

    INDEX
    Explanations

    barbecue

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     furnace
    0.66
     thermoplastics
    0.60
     barber
    0.57
     chisel
    0.57
     quadrupole
    0.56
    UST
    0.54
     condenser
    0.54
    届け
    0.54
     adiab
    0.54
    Butyl
    0.53
    POSITIVE LOGITS
     cues
    1.04
     Cue
    1.04
     cue
    1.03
    Cue
    0.96
    cue
    0.91
    hoe
    0.64
     cuer
    0.62
     Moe
    0.59
     cos
    0.57
     क्यू
    0.57
    Act Density 0.001%

    No Known Activations