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

    Neuronpedia

    INDEX
    Explanations

    Computer issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ічного
    -0.06
     coil
    -0.06
    اط
    -0.06
    explain
    -0.06
    Gravity
    -0.06
    िज
    -0.06
    şehir
    -0.06
    _test
    -0.05
    _SELECTION
    -0.05
    encrypt
    -0.05
    POSITIVE LOGITS
     هد
    0.07
     favorable
    0.07
    Ref
    0.07
    	labels
    0.07
    Figure
    0.07
    .DOM
    0.07
    uvre
    0.07
     phosphory
    0.07
     subtotal
    0.06
     aprove
    0.06
    Act Density 0.038%

    No Known Activations