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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ln
    -0.07
    .As
    -0.07
    十二
    -0.07
    身心
    -0.07
    .springframework
    -0.07
     Gamer
    -0.07
    /images
    -0.07
    .AllArgsConstructor
    -0.07
    /ng
    -0.06
    ahren
    -0.06
    POSITIVE LOGITS
    감
    0.07
     plates
    0.07
    _thr
    0.07
    蟲
    0.07
     wat
    0.07
    OT
    0.07
    虫
    0.06
    heet
    0.06
    bat
    0.06
    וע
    0.06
    Act Density 0.002%

    No Known Activations