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

    Neuronpedia

    INDEX
    Explanations

    things being named or called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -(
    0.38
    ive
    0.37
     They
    0.36
     Goes
    0.36
    (-
    0.35
     تمر
    0.35
     }=
    0.35
    <0x80>
    0.35
     Liberties
    0.35
    [-
    0.35
    POSITIVE LOGITS
     ediyoruz
    0.44
     ceea
    0.40
    ској
    0.40
     całość
    0.40
    祯
    0.38
    Cantidad
    0.37
     așa
    0.36
     timp
    0.36
     Fútbol
    0.36
     ecce
    0.36
    Act Density 0.071%

    No Known Activations