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

    Neuronpedia

    INDEX
    Explanations

    economics and production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (document
    -0.07
     unwilling
    -0.07
     Bea
    -0.07
    AccessToken
    -0.07
     SAVE
    -0.07
    Including
    -0.07
     Bubble
    -0.06
     여자
    -0.06
     dư
    -0.06
    oseconds
    -0.06
    POSITIVE LOGITS
    YGON
    0.06
     neon
    0.06
     Chester
    0.06
    /Instruction
    0.06
     bì
    0.06
    .is
    0.06
    iances
    0.06
    .data
    0.06
     latino
    0.06
     ethernet
    0.06
    Act Density 0.022%

    No Known Activations