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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tapes
    -0.07
    .Gr
    -0.07
     bricks
    -0.06
     Brick
    -0.06
     brick
    -0.06
     Roses
    -0.06
    vert
    -0.06
     ice
    -0.06
     sitesinde
    -0.06
     zat
    -0.06
    POSITIVE LOGITS
    /%
    0.07
    /",
    0.06
     Tecn
    0.06
     لر
    0.06
    _Account
    0.06
    /qt
    0.06
    (emp
    0.06
    /callback
    0.06
    登
    0.06
    ynom
    0.06
    Act Density 0.000%

    No Known Activations