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

    Neuronpedia

    INDEX
    Explanations

    oppositeley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    1.46
    ت
    1.27
    joints
    1.26
    pengaruhi
    1.26
    buyers
    1.21
    transfected
    1.20
    Z
    1.17
    these
    1.15
    K
    1.14
    the
    1.13
    POSITIVE LOGITS
     has
    1.25
    í
    1.16
    ä
    1.16
    ка
    1.10
    ü
    1.08
     water
    1.02
    eti
    0.99
    ene
    0.98
    ía
    0.97
     tennis
    0.95
    Act Density 0.000%

    No Known Activations