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

    Neuronpedia

    INDEX
    Explanations

    Future time reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _negative
    -0.07
    iki
    -0.06
     فار
    -0.06
     расп
    -0.06
    nými
    -0.06
     amacıyla
    -0.06
    Prince
    -0.06
     muchas
    -0.06
    Matcher
    -0.06
     política
    -0.06
    POSITIVE LOGITS
    	SDL
    0.07
    .he
    0.06
     Abb
    0.06
     pě
    0.06
    (script
    0.06
    ulkan
    0.06
     Coy
    0.06
     aa
    0.06
    /command
    0.06
    (in
    0.06
    Act Density 0.017%

    No Known Activations