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

    Neuronpedia

    INDEX
    Explanations

    technical documentation or procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aktivit
    0.46
     gubit
    0.43
     upgrading
    0.43
     imigr
    0.41
     configuring
    0.40
     बाध्य
    0.40
    Detal
    0.40
    書籍
    0.40
     biograf
    0.40
     financieras
    0.40
    POSITIVE LOGITS
     associated
    0.43
     ش
    0.39
     毛
    0.38
     through
    0.38
     inter
    0.38
     saturation
    0.37
    लेल्या
    0.37
     इंटर
    0.37
    relation
    0.37
     earth
    0.36
    Act Density 0.000%

    No Known Activations