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

    Neuronpedia

    INDEX
    Explanations

    lower bounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     socioeconomic
    -0.09
     forsk
    -0.09
     mosquito
    -0.08
     essentially
    -0.08
     Fon
    -0.08
     infatti
    -0.08
     celular
    -0.07
     vaulted
    -0.07
     feite
    -0.07
     tions
    -0.07
    POSITIVE LOGITS
     zumindest
    0.13
     almeno
    0.10
     ainakin
    0.10
     atleast
    0.08
    最低
    0.08
    至少
    0.08
     certainly
    0.08
    (seed
    0.08
    存在
    0.07
    지
    0.07
    Act Density 0.049%

    No Known Activations