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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    נכ
    -0.07
    搔
    -0.07
    ucher
    -0.07
    퐝
    -0.07
     heaps
    -0.07
     lar
    -0.06
    _PANEL
    -0.06
    _kel
    -0.06
    ✊
    -0.06
    -License
    -0.06
    POSITIVE LOGITS
     그리스
    0.07
    rift
    0.07
     proposed
    0.07
     meta
    0.07
     adress
    0.07
    _standard
    0.07
    .reset
    0.07
     mate
    0.06
    כר
    0.06
     HttpClient
    0.06
    Act Density 0.004%

    No Known Activations