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

    Neuronpedia

    INDEX
    Explanations

    mathematical equality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     edged
    -0.07
    阳城
    -0.06
     Fire
    -0.06
    �
    -0.06
     lsp
    -0.06
    _Display
    -0.06
    dma
    -0.05
     Gad
    -0.05
     obr
    -0.05
     flee
    -0.05
    POSITIVE LOGITS
     Fits
    0.07
     LIS
    0.07
    allowed
    0.07
    .(*
    0.07
    iten
    0.07
    Berry
    0.06
    REFERENCE
    0.06
    anchise
    0.06
    MAND
    0.06
    تبه
    0.06
    Act Density 0.028%

    No Known Activations