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

    Neuronpedia

    INDEX
    Explanations

    company leadership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nickname
    -0.07
    ेग
    -0.06
    .Z
    -0.06
    imator
    -0.06
    +'/
    -0.06
    eddar
    -0.06
    .cv
    -0.06
    -end
    -0.06
    _TAB
    -0.06
    ogan
    -0.06
    POSITIVE LOGITS
     evacuate
    0.07
     weaken
    0.07
     الحرب
    0.07
     commentators
    0.07
     označ
    0.06
     fury
    0.06
     mattresses
    0.06
     designate
    0.06
     Classification
    0.06
     जन
    0.06
    Act Density 0.011%

    No Known Activations