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

    Neuronpedia

    INDEX
    Explanations

    harmful and illegal content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    0.43
     картина
    0.38
     pomeriggio
    0.37
     AppBsky
    0.37
     surfaced
    0.37
    羋
    0.36
     सम्राट
    0.36
     citizen
    0.36
     chyba
    0.36
     smoke
    0.35
    POSITIVE LOGITS
    导师
    0.42
    稳定的
    0.40
    mentor
    0.40
    inten
    0.39
     Stabilization
    0.39
     inelastic
    0.38
     बोनस
    0.38
     stabilizing
    0.38
     stabilization
    0.37
    மதி
    0.37
    Act Density 0.002%

    No Known Activations