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

    Neuronpedia

    INDEX
    Explanations

    mathematical or technical explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    架
    0.41
     架
    0.40
    idé
    0.40
    qtd
    0.38
     Hey
    0.38
     Сле
    0.36
     Mathemat
    0.36
     प्रताप
    0.36
     Statements
    0.35
     Зна
    0.35
    POSITIVE LOGITS
     retention
    0.50
    Retention
    0.43
    ]={"
    0.42
     sneaky
    0.42
     rings
    0.40
     Retention
    0.39
     struts
    0.39
    "=>
    0.38
     irregularity
    0.38
    érêt
    0.38
    Act Density 0.000%

    No Known Activations