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

    Neuronpedia

    INDEX
    Explanations

    Debug messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -song
    -0.09
     comic
    -0.08
     incorporate
    -0.08
     constit
    -0.08
     incorporación
    -0.08
     incorpora
    -0.08
     innovative
    -0.08
    Survey
    -0.08
     rival
    -0.08
     vigente
    -0.08
    POSITIVE LOGITS
     pinpoint
    0.11
     clues
    0.10
     indicates
    0.09
     indicate
    0.09
     CWE
    0.09
     indicating
    0.09
     diagnosing
    0.09
     errno
    0.09
     bubbling
    0.09
    日志
    0.09
    Act Density 0.015%

    No Known Activations