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

    Neuronpedia

    INDEX
    Explanations

    error checking code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oot
    -0.08
     camouflage
    -0.08
    cached
    -0.08
     spring
    -0.08
    Cached
    -0.07
     Cached
    -0.07
     Curriculum
    -0.07
     finde
    -0.07
    ………
    -0.07
     cam
    -0.07
    POSITIVE LOGITS
    	perror
    0.11
    _failure
    0.11
     പരിശോധന
    0.10
     जांच
    0.10
     failures
    0.10
    检查
    0.09
     പരിശോധ
    0.09
     perror
    0.09
    _errors
    0.09
    _FAILURE
    0.09
    Act Density 0.004%

    No Known Activations