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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slaught
    -0.07
    ”),
    -0.07
     España
    -0.06
     [/
    -0.06
     '..',
    -0.06
    ODULE
    -0.06
     генера
    -0.06
    иля
    -0.06
     expelled
    -0.06
     harass
    -0.06
    POSITIVE LOGITS
    ıyı
    0.07
    encrypted
    0.06
     nuisance
    0.06
     teklif
    0.06
     bitch
    0.06
    	sql
    0.06
    /fonts
    0.06
    /home
    0.06
     vědom
    0.06
    yscale
    0.06
    Act Density 0.008%

    No Known Activations