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

    Neuronpedia

    INDEX
    Explanations

    device functionalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     callback
    -0.07
     terminated
    -0.07
    _end
    -0.07
    KHTML
    -0.06
    彼女
    -0.06
    得到
    -0.06
    _extraction
    -0.06
     Lau
    -0.06
    ець
    -0.06
     JScrollPane
    -0.06
    POSITIVE LOGITS
    .Contact
    0.07
     terör
    0.06
    flu
    0.06
     Pag
    0.06
     счит
    0.06
     Influ
    0.06
     objectively
    0.06
     announcements
    0.06
    .World
    0.06
    .Character
    0.06
    Act Density 0.269%

    No Known Activations