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

    Neuronpedia

    INDEX
    Explanations

    Reboot Nation resource links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    涳
    0.44
    晎
    0.42
    伱
    0.39
    হ্ন
    0.39
     हेली
    0.39
    წ
    0.39
    apanicola
    0.39
     배열
    0.38
    剻
    0.38
     твер
    0.38
    POSITIVE LOGITS
     El
    0.37
     signs
    0.36
     Amen
    0.36
    ém
    0.35
     Kne
    0.35
    lander
    0.35
     EMEA
    0.34
     ALL
    0.33
     Eminem
    0.33
     X
    0.33
    Act Density 0.019%

    No Known Activations