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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sits
    -0.06
     remain
    -0.06
    Slots
    -0.06
    	order
    -0.06
    keleton
    -0.06
    iture
    -0.06
     منظور
    -0.06
    Is
    -0.06
    political
    -0.06
     itemName
    -0.06
    POSITIVE LOGITS
    ="")↵
    0.07
     часа
    0.07
    .Sys
    0.07
    _DISP
    0.07
     oc
    0.07
     rak
    0.06
     moins
    0.06
     pavement
    0.06
    118
    0.06
     interviews
    0.06
    Act Density 0.021%

    No Known Activations