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

    Neuronpedia

    INDEX
    Explanations

    no required or absent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Each
    0.61
    ER
    0.60
    nur
    0.57
    Only
    0.56
    Thomas
    0.56
    With
    0.55
    Things
    0.55
    An
    0.55
    That
    0.54
    that
    0.53
    POSITIVE LOGITS
     longer
    0.88
     obstante
    0.77
     matter
    0.71
     ifs
    0.69
     entanto
    0.69
     appreciable
    0.68
     discernible
    0.67
    émie
    0.65
    zzles
    0.64
     shortage
    0.63
    Act Density 0.035%

    No Known Activations