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

    Neuronpedia

    INDEX
    Explanations

    range (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    乜
    1.00
    ৩৪
    0.99
    Balanced
    0.98
    scrollHeight
    0.97
    Phương
    0.97
     सहमति
    0.96
    0.94
    새
    0.94
    hemeral
    0.92
     obsolete
    0.92
    POSITIVE LOGITS
    ᵏ
    1.28
     冖
    1.17
     Markov
    1.09
     Их
    1.06
     kisah
    1.06
    arbre
    1.05
    lige
    1.04
     tanya
    1.04
    zhu
    1.04
     skyrock
    1.03
    Act Density 0.000%

    No Known Activations