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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gulp
    -0.07
    falls
    -0.07
     %#
    -0.07
    Gem
    -0.07
     Seks
    -0.07
    넝
    -0.06
    .{
    -0.06
    籽
    -0.06
    <?=$
    -0.06
     ingredient
    -0.06
    POSITIVE LOGITS
    VEN
    0.08
    截止
    0.07
    OP
    0.07
    ONTAL
    0.07
     différence
    0.07
     penalty
    0.07
    BERT
    0.07
    _BOX
    0.07
    Attrib
    0.07
    .cont
    0.07
    Act Density 0.002%

    No Known Activations