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

    Neuronpedia

    INDEX
    Explanations

    Substantial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ':'
    -0.06
     perpetrators
    -0.06
     Peters
    -0.06
    献
    -0.06
    ці
    -0.06
    反应
    -0.06
     Putin
    -0.06
     svens
    -0.06
    _Map
    -0.06
     відповідно
    -0.06
    POSITIVE LOGITS
    RED
    0.07
    coordinate
    0.07
     teasing
    0.07
    RANDOM
    0.07
     substantial
    0.07
     scalp
    0.07
     sach
    0.06
    ampp
    0.06
     DIST
    0.06
     vel
    0.06
    Act Density 0.000%

    No Known Activations