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

    Neuronpedia

    INDEX
    Explanations

    hardcover and paperback book types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বাঙ্গ
    0.43
    प्शन
    0.42
     AWAY
    0.40
    Tai
    0.39
     tagged
    0.38
     hom
    0.38
     Tai
    0.38
     Foundation
    0.37
     Hom
    0.37
    …”
    0.37
    POSITIVE LOGITS
     paperback
    0.88
     alkaline
    0.84
     alk
    0.75
     alkali
    0.75
     alkal
    0.75
     hardcover
    0.73
    alk
    0.72
    Alk
    0.70
     pb
    0.69
     binding
    0.66
    Act Density 0.001%

    No Known Activations