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

    Neuronpedia

    INDEX
    Explanations

    Technical drawbacks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    widget
    -0.07
     décor
    -0.07
    -cigaret
    -0.06
    ercial
    -0.06
    IZ
    -0.06
    Patient
    -0.06
    	let
    -0.06
     Friedman
    -0.06
    ican
    -0.06
     ух
    -0.06
    POSITIVE LOGITS
     Investment
    0.06
     Lynn
    0.06
    .ResponseBody
    0.06
     νέ
    0.06
    .scala
    0.06
    土
    0.06
     amsterdam
    0.06
     Slip
    0.06
     sloppy
    0.06
    _TOO
    0.06
    Act Density 0.109%

    No Known Activations