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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ……
    -0.06
    liche
    -0.06
    Limit
    -0.06
    mono
    -0.06
    picker
    -0.06
    .gen
    -0.06
    ling
    -0.06
    .Verify
    -0.06
    /Public
    -0.06
    LO
    -0.06
    POSITIVE LOGITS
    [idx
    0.07
     Mortgage
    0.06
     mortgage
    0.06
     �
    0.06
    ><?=$
    0.06
    braska
    0.06
    敗
    0.06
     -*-
    0.06
     gone
    0.06
    (created
    0.06
    Act Density 0.001%

    No Known Activations