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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Onion
    -0.07
     dust
    -0.07
     arcade
    -0.06
    (holder
    -0.06
     wireless
    -0.06
     wax
    -0.06
    FilterWhere
    -0.06
     goalkeeper
    -0.06
    (layout
    -0.06
    来了
    -0.06
    POSITIVE LOGITS
    様
    0.07
    /kubernetes
    0.06
    Κ
    0.06
    lw
    0.06
    ışma
    0.06
    /respond
    0.06
    .ps
    0.06
    _chg
    0.06
     바라
    0.06
    .pan
    0.06
    Act Density 0.032%

    No Known Activations