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

    Neuronpedia

    INDEX
    Explanations

    cannot do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Photo
    0.46
    Ps
    0.44
    Ｏ
    0.44
    TOP
    0.42
    SAMPLE
    0.42
    H
    0.42
    Half
    0.42
    Hayes
    0.41
    ж
    0.41
     ਇਕ
    0.41
    POSITIVE LOGITS
     maquin
    0.51
    굉장
    0.49
     estudio
    0.49
     abstra
    0.49
     acht
    0.49
     vivir
    0.47
    两种
    0.46
     biotechn
    0.46
     profes
    0.46
     aider
    0.46
    Act Density 0.003%

    No Known Activations