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

    Neuronpedia

    INDEX
    Explanations

    offers of further explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    **:
    0.66
    **,
    0.65
    :**
    0.63
    *,
    0.62
    ...",
    0.61
    *:
    0.60
    :",
    0.58
    :
    0.55
    …,
    0.54
    ”:
    0.54
    POSITIVE LOGITS
     Cheers
    0.77
     Hope
    0.74
     Thanks
    0.69
     saludos
    0.68
     hope
    0.67
    chevron
    0.66
     Wasch
    0.65
     Danke
    0.65
    awcy
    0.64
     Shame
    0.64
    Act Density 0.245%

    No Known Activations