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

    Neuronpedia

    INDEX
    Explanations

    Table formatting symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scholar
    -0.09
    Scholar
    -0.08
    .spring
    -0.08
     OECD
    -0.08
     conspiracy
    -0.08
    .issue
    -0.07
     semper
    -0.07
     annual
    -0.07
     huge
    -0.07
     subscribers
    -0.07
    POSITIVE LOGITS
    Elapsed
    0.15
    elapsed
    0.14
    _elapsed
    0.14
     elapsed
    0.13
    .elapsed
    0.13
     זמן
    0.12
     बित
    0.12
     زمن
    0.12
     시간을
    0.12
     دقائق
    0.12
    Act Density 0.019%

    No Known Activations