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
     úda
    -0.07
    myfile
    -0.07
     milit
    -0.07
     Giovanni
    -0.06
    487
    -0.06
    )$/
    -0.06
     pinpoint
    -0.06
     medidas
    -0.06
     sollten
    -0.06
    494
    -0.06
    POSITIVE LOGITS
     accepts
    0.13
     accept
    0.13
     accepted
    0.11
     Accept
    0.10
     acceptance
    0.10
    accept
    0.10
    Accept
    0.09
     accepting
    0.09
    ACCEPT
    0.09
    _ACCEPT
    0.09
    Act Density 0.017%

    No Known Activations