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

    Neuronpedia

    INDEX
    Explanations

    language model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     software
    0.73
     Software
    0.73
     recapture
    0.70
     logiciel
    0.69
     VRS
    0.67
    软件
    0.67
    昻
    0.67
     reinvent
    0.66
    立て
    0.65
    ографи
    0.65
    POSITIVE LOGITS
    🏼
    0.58
    models
    0.57
    Heavy
    0.54
     absorption
    0.53
    മോ
    0.53
    吸収
    0.52
    Models
    0.51
     பேச
    0.51
     Absorption
    0.51
     Mall
    0.50
    Act Density 0.263%

    No Known Activations