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

    Neuronpedia

    INDEX
    Explanations

    bilateral contract, unlimited bandwidth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mech
    0.43
     hábito
    0.39
    ʒ
    0.39
     соста
    0.39
     تە
    0.39
    regulated
    0.39
    idän
    0.38
     thụ
    0.38
    recycle
    0.38
     حی
    0.38
    POSITIVE LOGITS
     Dile
    0.42
     houve
    0.42
     흥
    0.42
    呠
    0.41
     schnell
    0.39
     Dette
    0.39
     Detta
    0.38
     absent
    0.38
     GND
    0.38
     not
    0.38
    Act Density 0.000%

    No Known Activations