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

    Neuronpedia

    INDEX
    Explanations

    handling different entities or situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contenuto
    0.53
    christian
    0.52
    videos
    0.52
     pressione
    0.52
     cristian
    0.51
    animation
    0.50
    Videos
    0.50
    actionMode
    0.49
     vidéos
    0.49
    Résumé
    0.49
    POSITIVE LOGITS
     hairy
    0.45
     take
    0.42
     आर्टिकल
    0.41
     Emperor
    0.41
    igree
    0.41
    일까지
    0.41
    ulosic
    0.41
    0.40
     Rakyat
    0.40
     feast
    0.40
    Act Density 0.001%

    No Known Activations