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

    Neuronpedia

    INDEX
    Explanations

    descriptive pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    വൻ
    0.39
    spiderX
    0.39
    వంటి
    0.38
    かもしれませんが
    0.38
    OpportunitiesBy
    0.37
    éticos
    0.37
    ใช้งาน
    0.37
    ennzeichnet
    0.37
    modelLogin
    0.36
    StarService
    0.35
    POSITIVE LOGITS
     contemporaneous
    0.38
     modifies
    0.37
     sneaky
    0.36
     flashbacks
    0.36
     stumpage
    0.36
     haircuts
    0.35
     flanking
    0.35
     leaks
    0.35
    .
    0.35
    ፍ
    0.35
    Act Density 0.784%

    No Known Activations