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

    Neuronpedia

    INDEX
    Explanations

    getting caught

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     학교
    -0.07
    .chars
    -0.06
    erin
    -0.06
     bakımından
    -0.06
    抱
    -0.06
    edl
    -0.06
    ansas
    -0.06
    maması
    -0.06
    -blocking
    -0.06
     hayır
    -0.06
    POSITIVE LOGITS
    <Group
    0.06
     mv
    0.06
    882
    0.06
     �
    0.06
    结
    0.06
     demographics
    0.06
    _option
    0.06
    ;↵↵↵↵
    0.06
     lunch
    0.06
    ;',↵
    0.06
    Act Density 0.098%

    No Known Activations