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

    Neuronpedia

    INDEX
    Explanations

    Login forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     School
    -0.07
    school
    -0.06
     Amerik
    -0.06
    Bat
    -0.06
     Bat
    -0.06
     kep
    -0.06
     mobs
    -0.06
     recurrent
    -0.06
     Mes
    -0.06
    ζη
    -0.06
    POSITIVE LOGITS
    _refs
    0.07
     mainland
    0.07
     )↵↵↵↵↵↵↵↵
    0.06
    .↵↵↵↵↵↵↵↵
    0.06
     blackjack
    0.06
    .Direct
    0.06
    .↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     nostalg
    0.06
    elial
    0.06
     użytk
    0.06
    Act Density 0.022%

    No Known Activations