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

    Neuronpedia

    INDEX
    Explanations

    gradle wrapper file

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     使っ
    0.40
    śa
    0.40
    entino
    0.40
    rexham
    0.39
    ),],
    0.38
     جذب
    0.38
    arken
    0.38
    橑
    0.38
    citealt
    0.37
    मक
    0.37
    POSITIVE LOGITS
     stuffed
    0.42
     preconditions
    0.40
    Wrapping
    0.40
     days
    0.40
     daily
    0.39
     stap
    0.37
     wrapped
    0.37
    Binder
    0.37
     included
    0.37
     փ
    0.36
    Act Density 0.001%

    No Known Activations