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

    Neuronpedia

    INDEX
    Explanations

    note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     versus
    -0.07
     недостат
    -0.06
     gore
    -0.06
    	str
    -0.06
     hoodie
    -0.06
     Nacht
    -0.06
    _ro
    -0.06
    怎
    -0.06
     HOR
    -0.06
    四
    -0.06
    POSITIVE LOGITS
    /name
    0.07
    หม
    0.06
    .undefined
    0.06
    .CODE
    0.06
     Hub
    0.06
    (question
    0.06
    فة
    0.06
    .g
    0.06
    vely
    0.06
     Participant
    0.06
    Act Density 0.000%

    No Known Activations