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

    Neuronpedia

    INDEX
    Explanations

    directed against other entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    噤
    0.49
    げる
    0.43
     көзге
    0.42
     rumoured
    0.41
    zął
    0.41
    bringen
    0.40
     sosyal
    0.39
     использоваться
    0.38
     bookService
    0.38
     వరకు
    0.38
    POSITIVE LOGITS
     instability
    0.43
     decay
    0.43
    decay
    0.43
     narrow
    0.41
     winding
    0.41
    intermediate
    0.41
     narrowing
    0.40
     broadening
    0.39
     filling
    0.39
    attachment
    0.39
    Act Density 0.000%

    No Known Activations