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

    Neuronpedia

    INDEX
    Explanations

    evaluate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pollen
    -0.08
    "net
    -0.07
     RelayCommand
    -0.07
    _system
    -0.07
    ースト
    -0.07
    Authorities
    -0.07
    �
    -0.07
    �
    -0.07
    Dependencies
    -0.06
    ³
    -0.06
    POSITIVE LOGITS
    Brain
    0.06
    izzie
    0.06
     )↵
    0.06
     ];
    0.06
     моз
    0.06
     elems
    0.06
    .ศ
    0.06
     escalating
    0.06
     Drinking
    0.05
     जग
    0.05
    Act Density 0.003%

    No Known Activations