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

    Neuronpedia

    INDEX
    Explanations

    files, attachments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stove
    -0.10
     mapping
    -0.08
     públicas
    -0.08
    mapping
    -0.08
     publieke
    -0.08
     publiques
    -0.08
     عوام
    -0.08
    公
    -0.07
     veřej
    -0.07
     verlichting
    -0.07
    POSITIVE LOGITS
     attachments
    0.15
     attachment
    0.14
    附件
    0.14
     Attach
    0.13
    Attachments
    0.13
    附
    0.13
    attachments
    0.13
     attached
    0.13
    Attachment
    0.12
     attach
    0.12
    Act Density 0.011%

    No Known Activations