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

    Neuronpedia

    INDEX
    Explanations

    groupId >

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    హ
    0.45
     Escal
    0.43
    рко
    0.41
    ံ့
    0.40
    மொ
    0.39
     Population
    0.38
    疵
    0.38
    𝚔
    0.37
    ప్‌
    0.37
    Drain
    0.36
    POSITIVE LOGITS
     nond
    0.42
     geo
    0.40
     awareness
    0.39
     trial
    0.39
    েলি
    0.38
     obscur
    0.38
     TEST
    0.37
     undetermined
    0.37
    aware
    0.37
     techno
    0.37
    Act Density 0.000%

    No Known Activations