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

    Neuronpedia

    INDEX
    Explanations

    mascot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.77
    "
    0.77
    ",
    0.73
    ...
    0.70
    िष्ट
    0.69
     scintill
    0.66
    ".
    0.64
      
    0.62
    ने
    0.62
    "...
    0.61
    POSITIVE LOGITS
     mascot
    1.07
     Mascot
    0.75
    ста
    0.74
    <0x80>
    0.70
     mascota
    0.70
    0
    0.69
    т
    0.67
    ૦
    0.66
    ological
    0.64
    اری
    0.64
    Act Density 0.001%

    No Known Activations