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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     molecules
    -0.09
    (cnt
    -0.08
    就意味着
    -0.07
    .tv
    -0.07
     immigr
    -0.07
    属于自己
    -0.07
    (memory
    -0.07
    _time
    -0.07
    بقى
    -0.07
     Signal
    -0.07
    POSITIVE LOGITS
    厦
    0.08
    wife
    0.07
     shower
    0.07
    _guide
    0.07
     opp
    0.06
    茂
    0.06
    \Persistence
    0.06
    讚
    0.06
    chsel
    0.06
    褂
    0.06
    Act Density 0.034%

    No Known Activations