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

    Neuronpedia

    INDEX
    Explanations

    additions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	version
    -0.07
     Plumbing
    -0.06
    uniform
    -0.06
     voted
    -0.06
    Current
    -0.06
     подв
    -0.06
     bearings
    -0.06
     дити
    -0.06
     VERSION
    -0.06
     eats
    -0.06
    POSITIVE LOGITS
    _fact
    0.07
    _dice
    0.07
    راد
    0.07
     kazanç
    0.06
     Scar
    0.06
    kaç
    0.06
    äß
    0.06
    :::::::::::
    0.06
    ⠀⠀
    0.06
    xin
    0.06
    Act Density 0.053%

    No Known Activations