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

    Neuronpedia

    INDEX
    Explanations

    moderator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uhn
    -0.08
    Nm
    -0.07
     df
    -0.07
    ahir
    -0.07
     Dương
    -0.07
    olution
    -0.07
    sip
    -0.07
    AYS
    -0.07
     adm
    -0.07
    孜
    -0.07
    POSITIVE LOGITS
    ครอบ
    0.07
    惊艳
    0.07
    gran
    0.07
     مقابل
    0.06
     roundup
    0.06
     isEqualToString
    0.06
    �
    0.06
     ברח
    0.06
     Solid
    0.06
     Emergency
    0.06
    Act Density 0.003%

    No Known Activations