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

    Neuronpedia

    INDEX
    Explanations

    strategy and misinformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ックス
    0.44
     fondness
    0.41
    ខ្សែ
    0.38
    GONE
    0.37
     சற்று
    0.37
     penchant
    0.36
    শব
    0.36
    $...
    0.36
    awcy
    0.36
    farwydd
    0.36
    POSITIVE LOGITS
    ដែលមាន
    0.43
     prov
    0.38
    umim
    0.37
     dimana
    0.37
    ായിക
    0.37
    Prov
    0.37
     Akad
    0.37
     mTOR
    0.37
     discharging
    0.36
     réalise
    0.36
    Act Density 0.000%

    No Known Activations