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

    Neuronpedia

    INDEX
    Explanations

    name followed by bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adsorb
    0.31
     ulcer
    0.31
    လိုအပ်
    0.29
     angle
    0.29
     exquisite
    0.29
     midwives
    0.29
    Genus
    0.29
     footpath
    0.29
    镞
    0.29
     tuberc
    0.28
    POSITIVE LOGITS
     தலைமையில்
    0.45
    aki
    0.36
     selaku
    0.34
    าร์
    0.33
    𓃵
    0.32
     Jr
    0.32
    担任
    0.32
     वकील
    0.31
    ško
    0.31
     mówi
    0.31
    Act Density 0.044%

    No Known Activations