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

    Neuronpedia

    INDEX
    Explanations

    exception handling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bachelor's
    -0.08
     gimm
    -0.08
     Graduation
    -0.08
     Beat
    -0.08
     gamble
    -0.08
     Rolex
    -0.08
     contamos
    -0.07
    雄
    -0.07
     Sculpt
    -0.07
    Beat
    -0.07
    POSITIVE LOGITS
     informative
    0.12
     gracefully
    0.11
     информ
    0.11
     stderr
    0.10
     appropriate
    0.10
     graceful
    0.10
     Appropriate
    0.10
    .notify
    0.09
    .retry
    0.09
     angem
    0.09
    Act Density 0.012%

    No Known Activations