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

    Neuronpedia

    INDEX
    Explanations

    towel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rare
    -0.07
     decisions
    -0.07
     rare
    -0.06
    .Resume
    -0.06
    -ra
    -0.06
    uition
    -0.06
     mi
    -0.06
     identifying
    -0.06
    Overrides
    -0.06
    Param
    -0.06
    POSITIVE LOGITS
     towel
    0.08
     Fib
    0.07
    λλα
    0.06
    .Stderr
    0.06
     openFileDialog
    0.06
    .caption
    0.06
    ogo
    0.06
     Locker
    0.06
    $(".
    0.06
    Ông
    0.06
    Act Density 0.001%

    No Known Activations