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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [l
    -0.06
    pData
    -0.06
    ^K
    -0.06
    /D
    -0.06
    .nom
    -0.06
     legitimacy
    -0.06
    Typography
    -0.05
     Assy
    -0.05
     usernames
    -0.05
     bourgeois
    -0.05
    POSITIVE LOGITS
    抬
    0.07
    _loop
    0.06
     reconstruct
    0.06
    SSIP
    0.06
    騎
    0.06
    iconductor
    0.06
    unter
    0.06
     confirm
    0.06
    aster
    0.06
    .Keys
    0.06
    Act Density 0.001%

    No Known Activations