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

    Neuronpedia

    INDEX
    Explanations

    preparing requirements at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mod
    0.37
     hiding
    0.35
    ত্রের
    0.35
     hesitated
    0.35
     ungu
    0.35
    侸
    0.35
     योज
    0.34
     moderators
    0.34
     தை
    0.34
    was
    0.34
    POSITIVE LOGITS
    لاه
    0.39
     internazionale
    0.38
    하다
    0.38
     invertebrate
    0.38
    \|=
    0.38
    !="
    0.38
     आदी
    0.38
    लेला
    0.38
    ignan
    0.37
     Byrne
    0.36
    Act Density 0.000%

    No Known Activations