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

    Neuronpedia

    INDEX
    Explanations

    slightly, particularly, most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alcuna
    1.14
     كما
    1.13
     μια
    1.07
    ের
    1.03
     և
    1.02
    s
    1.01
     及び
    1.00
    及び
    0.96
    sine
    0.96
    도
    0.96
    POSITIVE LOGITS
     ocult
    1.17
     nbsp
    1.16
     axiom
    1.15
     squadron
    1.14
     battalion
    1.07
     origami
    1.05
     turban
    1.04
    0
    1.03
     bisque
    1.02
     tablespoon
    1.02
    Act Density 0.337%

    No Known Activations