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

    Neuronpedia

    INDEX
    Explanations

    hawk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     приг
    -0.07
     เป
    -0.07
    insi
    -0.07
     procession
    -0.07
    eti
    -0.06
    ันเป
    -0.06
    ombre
    -0.06
    рой
    -0.06
    .indices
    -0.06
    不安
    -0.06
    POSITIVE LOGITS
     Haw
    0.15
     Hawk
    0.11
    aw
    0.11
     hawk
    0.11
    hawk
    0.11
     Shaw
    0.10
     Daw
    0.10
     Hawks
    0.10
    AW
    0.09
     Gaw
    0.08
    Act Density 0.008%

    No Known Activations