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

    Neuronpedia

    INDEX
    Explanations

    breaking down and explaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eze
    0.50
     Highways
    0.46
    恸
    0.46
    เชสเตอร์
    0.45
     fugitive
    0.44
    atation
    0.44
    Архі
    0.43
     fluence
    0.43
    ခန်း
    0.42
     Directories
    0.42
    POSITIVE LOGITS
     consisting
    0.50
     consists
    0.47
    xb
    0.45
    groupBy
    0.45
     summarizes
    0.45
    ấp
    0.44
     reproduces
    0.44
     boven
    0.43
     posle
    0.43
     relies
    0.42
    Act Density 0.005%

    No Known Activations