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

    Neuronpedia

    INDEX
    Explanations

    technical/academic text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =
↵
    -0.07
     swim
    -0.07
    ._↵
    -0.07
    ,...↵
    -0.06
    海
    -0.06
     	↵
    -0.06
    .;↵
    -0.06
    SS
    -0.06
     दर
    -0.06
    ;\
    -0.06
    POSITIVE LOGITS
     oben
    0.07
     Closure
    0.06
    reste
    0.06
     guarda
    0.06
    _HC
    0.06
    _handlers
    0.06
    �
    0.06
     seated
    0.06
    	Int
    0.06
     enthusiastic
    0.06
    Act Density 0.459%

    No Known Activations