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

    Neuronpedia

    INDEX
    Explanations

    you can use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Princ
    0.51
    Theory
    0.48
    Implement
    0.48
     실시
    0.47
     Aal
    0.47
    Search
    0.46
    Install
    0.46
    탈
    0.46
    Models
    0.46
    Companies
    0.46
    POSITIVE LOGITS
    üng
    0.48
    ipak
    0.47
     autoWatch
    0.47
    y
    0.46
     reproductions
    0.46
     honed
    0.46
    ⤴
    0.46
    iong
    0.45
    eworthy
    0.45
     attainment
    0.45
    Act Density 0.000%

    No Known Activations