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

    Neuronpedia

    INDEX
    Explanations

    research analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лату
    -0.07
    jaw
    -0.07
     Lew
    -0.06
     cấp
    -0.06
     Auto
    -0.06
    slide
    -0.06
     Heat
    -0.06
    ки
    -0.06
     freak
    -0.06
     bastard
    -0.06
    POSITIVE LOGITS
     eigen
    0.07
    톡
    0.06
     REGISTER
    0.06
    _marshall
    0.06
    :add
    0.06
     `↵
    0.06
     printk
    0.06
     Relay
    0.06
     常
    0.06
     hath
    0.06
    Act Density 0.050%

    No Known Activations