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

    Neuronpedia

    INDEX
    Explanations

    A Deep Dive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …]
    0.42
    ……………………
    0.42
     casos
    0.42
    ...."
    0.41
    ……..
    0.40
    ・・・・
    0.40
    واقع
    0.40
    ………..
    0.40
     excepciones
    0.40
    testimon
    0.40
    POSITIVE LOGITS
     Explained
    1.20
     explained
    1.06
     dive
    1.03
     deep
    1.02
     Deep
    1.02
     Dive
    1.02
     delves
    0.97
     delve
    0.94
     dives
    0.91
     delving
    0.91
    Act Density 0.172%

    No Known Activations