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

    Neuronpedia

    INDEX
    Explanations

    Common grammatical connectors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obscene
    -0.08
    ılıyor
    -0.08
    _hard
    -0.08
    制品
    -0.08
    (nome
    -0.07
    觚
    -0.07
     ........
    -0.07
     vết
    -0.07
    (MenuItem
    -0.07
     tonight
    -0.07
    POSITIVE LOGITS
     complaining
    0.08
    達
    0.07
    	l
    0.07
    住在
    0.07
    ἂ
    0.07
    準
    0.07
    compass
    0.07
    SP
    0.07
    Their
    0.07
    [url
    0.07
    Act Density 0.005%

    No Known Activations