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

    Neuronpedia

    INDEX
    Explanations

    there is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exists
    0.50
    が存在
    0.43
     hasn
    0.43
    existe
    0.41
     NEEDS
    0.41
    pecific
    0.41
     existent
    0.40
     wasn
    0.39
    exists
    0.39
    appy
    0.38
    POSITIVE LOGITS
    বলের
    0.40
     stroj
    0.39
     dur
    0.38
     መጠን
    0.38
     praz
    0.37
    Interactor
    0.37
     platz
    0.37
    Dur
    0.37
    λογ
    0.35
    ucía
    0.35
    Act Density 0.001%

    No Known Activations