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

    Neuronpedia

    INDEX
    Explanations

    context is key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olarak
    0.21
     Anyways
    0.21
    ណ្ត
    0.21
     Temperatura
    0.21
     Daarnaast
    0.20
     Hãy
    0.20
     Außerdem
    0.20
     Became
    0.20
     акысыз
    0.20
     عندما
    0.20
    POSITIVE LOGITS
     сто
    0.23
    devices
    0.23
     obvious
    0.22
    *
    0.21
     ψ
    0.20
     evol
    0.19
    lf
    0.19
    ופ
    0.19
    *>
    0.19
    ders
    0.18
    Act Density 0.000%

    No Known Activations