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

    Neuronpedia

    INDEX
    Explanations

    Math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (link
    -0.07
    .throw
    -0.07
     techn
    -0.07
    nav
    -0.07
    ow
    -0.07
     frü
    -0.06
     federal
    -0.06
    OW
    -0.06
    Nome
    -0.06
    ky
    -0.06
    POSITIVE LOGITS
    ı
    0.06
     перест
    0.06
    )↵↵↵↵↵↵
    0.06
    โพ
    0.06
    _CO
    0.06
    _probs
    0.06
     слож
    0.06
    .Execution
    0.06
     Shaman
    0.06
    	elseif
    0.06
    Act Density 0.025%

    No Known Activations