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

    Neuronpedia

    INDEX
    Explanations

    economy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     genç
    -0.08
     DCHECK
    -0.07
     TString
    -0.07
    defgroup
    -0.07
    ccione
    -0.07
     Kra
    -0.07
    䐃
    -0.07
     magnetic
    -0.07
    ptime
    -0.07
    belie
    -0.06
    POSITIVE LOGITS
    /model
    0.07
     Soap
    0.07
    /C
    0.07
    跡
    0.07
    "A
    0.06
    צעד
    0.06
     לעבוד
    0.06
    เข
    0.06
    역
    0.06
    "){
↵
    0.06
    Act Density 0.044%

    No Known Activations