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

    Neuronpedia

    INDEX
    Explanations

    increase

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ись
    -0.08
    	SET
    -0.07
    して
    -0.07
     tinder
    -0.07
    _ac
    -0.07
    rick
    -0.07
    _agents
    -0.06
    .sex
    -0.06
    (hostname
    -0.06
    (chip
    -0.06
    POSITIVE LOGITS
    ULLET
    0.07
     خوبی
    0.06
    EEE
    0.06
    cow
    0.06
     candies
    0.06
     가능
    0.06
    -stock
    0.06
     sworn
    0.06
     některých
    0.05
     Spanish
    0.05
    Act Density 0.017%

    No Known Activations