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

    Neuronpedia

    INDEX
    Explanations

    og

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nir
    -0.06
     sehr
    -0.06
    δει
    -0.06
     BK
    -0.06
    act
    -0.06
    řeb
    -0.06
    DisplayName
    -0.06
     chant
    -0.06
    _L
    -0.06
     Kr
    -0.06
    POSITIVE LOGITS
    _TEAM
    0.07
     tuo
    0.07
     Todo
    0.07
     tisí
    0.07
     Instances
    0.07
    τύ
    0.07
     teach
    0.07
    想到
    0.06
    todo
    0.06
     pharmacies
    0.06
    Act Density 0.013%

    No Known Activations