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

    Neuronpedia

    INDEX
    Explanations

    photo or Getty Image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ideals
    0.85
    azing
    0.75
     digestion
    0.72
     integrals
    0.72
     values
    0.72
     spices
    0.71
     axioms
    0.70
     pondered
    0.69
     qualitative
    0.69
    åg
    0.69
    POSITIVE LOGITS
    Photo
    2.06
     Photo
    1.97
    Photograph
    1.71
    Foto
    1.64
     photo
    1.64
    photo
    1.60
     Getty
    1.59
    PHOTO
    1.55
     Foto
    1.54
    Getty
    1.54
    Act Density 0.009%

    No Known Activations