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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     latin
    -0.06
     podmín
    -0.06
    uestos
    -0.06
    姑
    -0.06
    )]);↵
    -0.06
    '}}>
    -0.06
    acích
    -0.06
     책
    -0.06
    ='".$
    -0.05
     dissip
    -0.05
    POSITIVE LOGITS
     bật
    0.07
    GreaterThan
    0.07
     architectural
    0.07
    -handed
    0.06
    0.06
     folder
    0.06
     Nottingham
    0.06
    .Console
    0.06
    chai
    0.06
    她的
    0.06
    Act Density 0.015%

    No Known Activations