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

    Neuronpedia

    INDEX
    Explanations

    nationalities followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ul
    0.37
     orgánica
    0.37
    <unused272>
    0.34
    azität
    0.33
     patitth
    0.33
    <unused685>
    0.33
    <unused1125>
    0.33
    ur
    0.33
    <unused656>
    0.33
    <unused2040>
    0.33
    POSITIVE LOGITS
     be
    0.44
    ↵
    0.36
    س
    0.34
     than
    0.31
            
    0.30
    IN
    0.30
     an
    0.29
    FC
    0.29
    -
    0.29
    FAMILY
    0.29
    Act Density 0.378%

    No Known Activations