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

    Neuronpedia

    INDEX
    Explanations

    odium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ",{
    -0.07
    *",
    -0.07
     Sick
    -0.07
     Jing
    -0.06
     Lesb
    -0.06
     DIV
    -0.06
     Barn
    -0.06
     �
    -0.06
    ียนบ
    -0.06
     Rud
    -0.06
    POSITIVE LOGITS
     sodium
    0.09
    049
    0.08
    leanor
    0.07
    珠
    0.07
    income
    0.07
     Naomi
    0.07
     Neptune
    0.07
     Sodium
    0.07
    rahim
    0.07
    gravity
    0.07
    Act Density 0.008%

    No Known Activations