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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arcs
    -0.07
     neob
    -0.07
     robes
    -0.06
    iel
    -0.06
    radu
    -0.06
    .INVALID
    -0.06
    PostBack
    -0.06
     educator
    -0.06
    permalink
    -0.06
     اشاره
    -0.06
    POSITIVE LOGITS
    MatrixMode
    0.06
    sq
    0.06
     computers
    0.06
    Twenty
    0.06
    registro
    0.06
    ="${
    0.06
    обра�
    0.06
    मक
    0.06
    690
    0.06
    686
    0.06
    Act Density 0.000%

    No Known Activations