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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hol
    -0.06
     Ep
    -0.06
    Waiting
    -0.06
     Pikachu
    -0.06
     byte
    -0.06
    fixed
    -0.06
     heads
    -0.06
     Thu
    -0.06
     ضو
    -0.06
     succ
    -0.06
    POSITIVE LOGITS
     naveg
    0.07
    imension
    0.06
    -special
    0.06
     당시
    0.06
    Ｍ
    0.06
    arbeit
    0.06
    ellidos
    0.06
    (mut
    0.06
    ouncil
    0.06
    odem
    0.06
    Act Density 0.035%

    No Known Activations