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

    Neuronpedia

    INDEX
    Explanations

    Challenging the status quo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ах
    -0.08
     발매
    -0.07
     же
    -0.07
     wides
    -0.07
    ภาษ
    -0.07
    _filt
    -0.06
     judge
    -0.06
     οργ
    -0.06
    _ind
    -0.06
     petals
    -0.06
    POSITIVE LOGITS
    interop
    0.06
    /backend
    0.06
    iosity
    0.06
    减
    0.06
    付き
    0.06
    阅
    0.05
    =\""
    0.05
    ==$
    0.05
     ayr
    0.05
     Abu
    0.05
    Act Density 0.033%

    No Known Activations