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

    Neuronpedia

    INDEX
    Explanations

    allows, permits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ansiedad
    0.45
     불안
    0.43
    شرين
    0.43
     Equestrian
    0.43
    스포츠
    0.40
     ada
    0.38
     anxiety
    0.38
    ائف
    0.38
     Aug
    0.38
     Lund
    0.38
    POSITIVE LOGITS
    ovol
    0.41
     overcome
    0.38
     wilt
    0.37
    opic
    0.37
    cob
    0.37
    ωνα
    0.37
    ouro
    0.37
    owls
    0.37
     prover
    0.37
     වී
    0.36
    Act Density 0.001%

    No Known Activations