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

    Neuronpedia

    INDEX
    Explanations

    source attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grammatical
    0.38
     conflic
    0.38
     stoichi
    0.36
     veines
    0.35
     interessant
    0.35
     deterioration
    0.34
     lenguaje
    0.34
     singularities
    0.34
     veineux
    0.34
     treatises
    0.34
    POSITIVE LOGITS
     Photo
    0.80
    Photo
    0.79
     photo
    0.73
    photo
    0.70
     Courtesy
    0.69
     Foto
    0.69
     Photographer
    0.67
    Foto
    0.66
     photographer
    0.64
     Photography
    0.63
    Act Density 0.003%

    No Known Activations