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

    Neuronpedia

    INDEX
    Explanations

    Salut, 젠장, pH levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mediators
    0.50
     mediate
    0.47
     compartmental
    0.47
     firewall
    0.46
     norepinephrine
    0.46
     niektor
    0.46
     neurons
    0.46
     sphincter
    0.46
     hardcore
    0.45
     tokamak
    0.45
    POSITIVE LOGITS
    }{
    0.44
    匆
    0.44
    ท
    0.43
    ên
    0.43
    已有
    0.43
    })$.
    0.42
    先前
    0.40
     {
    0.40
    ця
    0.40
    ève
    0.39
    Act Density 0.013%

    No Known Activations