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

    Neuronpedia

    INDEX
    Explanations

    concepts followed by outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.48
    ar
    0.47
    attia
    0.46
    ა
    0.46
    aworld
    0.45
    ot
    0.45
    rax
    0.45
    jaer
    0.44
    quered
    0.44
    reated
    0.43
    POSITIVE LOGITS
     âng
    0.49
     ah
    0.48
     CME
    0.47
     aha
    0.45
    ﺒ
    0.45
     son
    0.44
     size
    0.44
     triangular
    0.44
     Như
    0.44
     thúc
    0.44
    Act Density 0.004%

    No Known Activations