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

    Neuronpedia

    INDEX
    Explanations

    artistic and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     %+
    0.50
     каби
    0.46
    ementara
    0.45
     enables
    0.43
    嗳
    0.43
    仹
    0.43
    狧
    0.42
    baseHP
    0.42
    olari
    0.41
     precludes
    0.41
    POSITIVE LOGITS
     Cup
    0.54
    s
    0.50
     slogan
    0.48
    isman
    0.45
     s
    0.45
     contrat
    0.44
    :
    0.44
    <start_of_image>
    0.44
     Instagram
    0.44
     e
    0.44
    Act Density 0.001%

    No Known Activations