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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _normal
    -0.07
    xy
    -0.06
     Stores
    -0.06
    _related
    -0.06
    وي
    -0.06
    리
    -0.06
     Duc
    -0.06
    _accept
    -0.06
     mods
    -0.06
    	assert
    -0.06
    POSITIVE LOGITS
     Money
    0.07
     �
    0.06
     expensive
    0.06
     Jed
    0.06
    .RemoveAt
    0.06
     проблемы
    0.06
     scop
    0.06
     gift
    0.06
    ］
    0.06
     bulunuyor
    0.06
    Act Density 0.001%

    No Known Activations