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

    Neuronpedia

    INDEX
    Explanations

    spyware and information theft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ten
    0.67
    er
    0.66
    ed
    0.64
    en
    0.63
    ↵↵
    0.61
     time
    0.61
    ized
    0.61
    time
    0.60
    post
    0.60
    un
    0.58
    POSITIVE LOGITS
     DISPLAYS
    0.64
    RENT
    0.59
    蓁
    0.57
    ὧ
    0.56
    ERS
    0.56
     spinors
    0.55
    ⓪
    0.55
     QSOs
    0.55
     encomendas
    0.54
     OXIDES
    0.54
    Act Density 0.000%

    No Known Activations