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

    Neuronpedia

    INDEX
    Explanations

    startups, frameworks, ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     central
    0.38
    Locks
    0.36
     locks
    0.36
     Estimate
    0.36
     Estimates
    0.36
     Zone
    0.35
     clergy
    0.35
     Developers
    0.35
    Develop
    0.35
     궁
    0.35
    POSITIVE LOGITS
     לנ
    0.41
    名的
    0.40
     bụi
    0.40
    াইন
    0.39
     ullamcorper
    0.39
     শুক
    0.39
    undaria
    0.38
    掄
    0.38
    roph
    0.38
    炔
    0.38
    Act Density 0.000%

    No Known Activations