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

    Neuronpedia

    INDEX
    Explanations

    quoted closing statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerous
    0.79
    蓦
    0.79
    +:
    0.69
     myriad
    0.69
     Initially
    0.67
     Later
    0.64
     Often
    0.64
    ించిన
    0.64
     puriso
    0.63
    laden
    0.63
    POSITIVE LOGITS
    .”
    3.38
    。」
    3.31
    ."
    3.29
    。”
    3.27
    .”)
    3.14
    .")
    3.13
    ."]
    3.00
    .’’
    2.88
    .").
    2.84
    .\"
    2.84
    Act Density 0.964%

    No Known Activations