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

    Neuronpedia

    INDEX
    Explanations

    objective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nuxtjs
    0.44
    ruary
    0.43
    pras
    0.43
     pemasaran
    0.43
    берриз
    0.42
    掮
    0.41
    Altura
    0.40
    illeurs
    0.40
    ליה
    0.39
    <unused545>
    0.39
    POSITIVE LOGITS
     not
    0.57
     fundamentally
    0.52
     nothing
    0.47
     existent
    0.47
     exist
    0.46
     model
    0.45
     create
    0.45
     assign
    0.45
     irreversible
    0.45
     without
    0.44
    Act Density 0.002%

    No Known Activations