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

    Neuronpedia

    INDEX
    Explanations

    random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SAME
    -0.08
     Télé
    -0.07
    IMATE
    -0.07
     Income
    -0.06
    ithe
    -0.06
    -Y
    -0.06
     Tamb
    -0.06
     också
    -0.06
    ;set
    -0.06
    adier
    -0.06
    POSITIVE LOGITS
     tm
    0.07
     finalists
    0.07
     exce
    0.07
    _vc
    0.06
    使
    0.06
     protesting
    0.06
     biomass
    0.06
     finals
    0.06
     Народ
    0.06
    Ac
    0.06
    Act Density 0.000%

    No Known Activations