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

    Neuronpedia

    INDEX
    Explanations

    function arguments in documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒀕
    0.42
    澥
    0.40
    ිබ
    0.39
    њима
    0.37
     getName
    0.37
     SIGNAL
    0.37
    ∕
    0.37
    ſh
    0.36
     //#
    0.36
     JERSEY
    0.35
    POSITIVE LOGITS
     takes
    0.75
    ."""
    0.72
    Args
    0.71
     Returns
    0.67
     принимает
    0.66
     Takes
    0.66
    """
    0.63
     Provides
    0.63
     Args
    0.62
     receives
    0.60
    Act Density 0.064%

    No Known Activations