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

    Neuronpedia

    INDEX
    Explanations

    quoted speech or dialogue starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ("
    0.44
     (“
    0.43
     divisor
    0.41
     ведь
    0.40
     humor
    0.39
     delimit
    0.39
     servlet
    0.39
     też
    0.39
     scopes
    0.37
     shaders
    0.37
    POSITIVE LOGITS
    The
    0.90
    This
    0.88
    There
    0.87
    We
    0.86
    It
    0.84
    You
    0.83
    They
    0.82
    In
    0.81
    On
    0.80
    When
    0.80
    Act Density 0.111%

    No Known Activations