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

    Neuronpedia

    INDEX
    Explanations

    squaring rhyme cuenta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wal
    0.53
    Dirty
    0.52
    Model
    0.49
    Doctors
    0.49
    Hero
    0.48
    Composite
    0.47
     wal
    0.47
    Health
    0.47
    Epoch
    0.47
    Access
    0.47
    POSITIVE LOGITS
    uert
    0.51
     ingredientes
    0.50
    vyš
    0.50
    erté
    0.48
    ümer
    0.47
    vés
    0.47
     ungew
    0.47
     abstractions
    0.47
    ük
    0.46
     دي
    0.46
    Act Density 0.001%

    No Known Activations