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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gener
    -0.07
     패
    -0.07
     Thesis
    -0.06
    ufac
    -0.06
    eses
    -0.06
     Xunit
    -0.06
    談
    -0.06
    ativa
    -0.06
     mamma
    -0.06
    Rew
    -0.06
    POSITIVE LOGITS
     boxer
    0.07
    xi
    0.07
     Palmer
    0.07
    TextField
    0.06
    .array
    0.06
    قد
    0.06
    tele
    0.06
     ""↵↵
    0.06
    fm
    0.06
     WLAN
    0.06
    Act Density 0.018%

    No Known Activations