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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ay
    -0.08
    Server
    -0.07
     patent
    -0.06
     *}↵↵
    -0.06
    .android
    -0.06
    "url
    -0.06
    ackBar
    -0.06
    avin
    -0.06
     escort
    -0.06
     negate
    -0.06
    POSITIVE LOGITS
     Specifications
    0.07
     reinforce
    0.07
    freq
    0.06
    forced
    0.06
     Expr
    0.06
     θέση
    0.06
     titten
    0.06
    είται
    0.06
    tahun
    0.06
    BYTE
    0.06
    Act Density 0.017%

    No Known Activations