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

    Neuronpedia

    INDEX
    Explanations

    accept

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    487
    -0.08
     study
    -0.08
    Data
    -0.07
     Fig
    -0.07
     Grove
    -0.07
     drives
    -0.07
     Study
    -0.07
    488
    -0.07
    耗
    -0.06
    508
    -0.06
    POSITIVE LOGITS
     accepted
    0.15
     accept
    0.15
     accepts
    0.13
     accepting
    0.13
     Accept
    0.12
     acceptance
    0.12
    accept
    0.10
    Accept
    0.10
     ACCEPT
    0.10
     acept
    0.10
    Act Density 0.022%

    No Known Activations