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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ustry
    -0.07
    442
    -0.07
     менше
    -0.07
    igar
    -0.06
    -fields
    -0.06
    ecies
    -0.06
    -0.06
    _iter
    -0.06
     sedm
    -0.06
    (Vec
    -0.06
    POSITIVE LOGITS
    DL
    0.07
    due
    0.06
     bootloader
    0.06
     Česk
    0.06
    нош
    0.06
    OPTIONS
    0.06
     ResponseEntity
    0.06
    ??
    0.06
     QC
    0.06
     Schema
    0.06
    Act Density 0.001%

    No Known Activations