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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     granularity
    -0.06
     mustard
    -0.06
    िछल
    -0.05
     Perspective
    -0.05
     
↵
↵
    -0.05
    udem
    -0.05
    模型
    -0.05
    观
    -0.05
     że
    -0.05
    搜
    -0.05
    POSITIVE LOGITS
     moto
    0.07
     asi
    0.06
    ENCIES
    0.06
    acağını
    0.06
    0.06
     :/
    0.06
     Xperia
    0.06
     PLEASE
    0.06
    ա
    0.06
     preserved
    0.06
    Act Density 0.010%

    No Known Activations