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

    Neuronpedia

    INDEX
    Explanations

    Legal citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skład
    -0.07
    ניג
    -0.07
     Sellers
    -0.07
     cellForRowAt
    -0.07
     traps
    -0.06
    /no
    -0.06
    -themed
    -0.06
     gym
    -0.06
    _DC
    -0.06
    ☤
    -0.06
    POSITIVE LOGITS
    等一批
    0.08
    	account
    0.07
     équipé
    0.07
     придется
    0.07
     European
    0.07
    tlement
    0.07
     Vatican
    0.07
    zhou
    0.07
    (protocol
    0.07
    HAS
    0.07
    Act Density 0.003%

    No Known Activations