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

    Neuronpedia

    INDEX
    Explanations

    gentle safety issues short hair

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reflectivity
    0.44
    Checkbox
    0.41
     Flats
    0.40
     Flat
    0.39
     flatness
    0.39
     reflectance
    0.38
    オク
    0.38
    Flat
    0.37
    Observer
    0.37
     LEDs
    0.36
    POSITIVE LOGITS
     short
    0.40
     gentle
    0.39
     proté
    0.39
     coats
    0.37
     rövid
    0.36
    丁寧
    0.36
    laştır
    0.36
     pile
    0.35
     Kalyan
    0.35
     nervous
    0.35
    Act Density 0.000%

    No Known Activations