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

    Neuronpedia

    INDEX
    Explanations

    Project

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mannit
    0.53
     eyelid
    0.50
    lur
    0.49
    ead
    0.49
     lymphatiques
    0.49
     evasion
    0.48
    onycha
    0.47
    サングラス
    0.45
    levi
    0.45
    댈
    0.44
    POSITIVE LOGITS
    Project
    3.50
     project
    3.49
     Project
    3.45
    project
    3.34
     Projects
    3.21
     projects
    3.13
     Projekt
    2.98
     PROJECT
    2.95
    projects
    2.92
    Projekt
    2.88
    Act Density 0.535%

    No Known Activations