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

    Neuronpedia

    INDEX
    Explanations

    therapy/education

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ेक
    -0.07
     devices
    -0.07
     weekday
    -0.07
    -0.06
    .course
    -0.06
     roku
    -0.06
    \Common
    -0.06
    .asc
    -0.06
    _station
    -0.06
     ـ
    -0.06
    POSITIVE LOGITS
    halt
    0.07
    -Cs
    0.07
    decoded
    0.06
    HZ
    0.06
    -cont
    0.06
    gap
    0.06
    Grammar
    0.06
     hamm
    0.06
    Recognition
    0.06
    	assertThat
    0.06
    Act Density 0.024%

    No Known Activations