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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    410
    -0.07
    .”↵↵
    -0.07
     entrepreneurs
    -0.07
    Boxes
    -0.07
    Specification
    -0.06
    .mc
    -0.06
    Moving
    -0.06
     stared
    -0.06
     benchmarks
    -0.06
     supervised
    -0.06
    POSITIVE LOGITS
     дів
    0.07
    lyphicon
    0.06
    sizlik
    0.06
    ensa
    0.06
     наче
    0.06
    UGHT
    0.06
    iverz
    0.06
     člověk
    0.06
    tica
    0.06
    医疗
    0.06
    Act Density 0.198%

    No Known Activations