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

    Neuronpedia

    INDEX
    Explanations

    say "ense"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
     knex
    -0.06
    网投
    -0.06
     reward
    -0.06
    坭
    -0.06
    -Israel
    -0.06
    redni
    -0.06
     teste
    -0.06
     socio
    -0.06
     causal
    -0.06
    POSITIVE LOGITS
    함
    0.07
    .serv
    0.07
     بواسطة
    0.07
     sensors
    0.07
    不仅是
    0.06
    .CONT
    0.06
    Option
    0.06
    0.06
     [("
    0.06
    izont
    0.06
    Act Density 0.005%

    No Known Activations