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

    Neuronpedia

    INDEX
    Explanations

    months or "in"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    resse
    -0.07
    ynn
    -0.06
    极大地
    -0.06
    ARSER
    -0.06
    _TAGS
    -0.06
    周一
    -0.06
    ("%.
    -0.06
    glyphicon
    -0.06
     ידי
    -0.06
    (TRUE
    -0.06
    POSITIVE LOGITS
     album
    0.07
    ⾼
    0.07
     UINT
    0.07
    !</
    0.07
     Wang
    0.07
    Ticket
    0.07
     dynamically
    0.07
    _with
    0.07
     <%
    0.07
    Variant
    0.07
    Act Density 0.001%

    No Known Activations

    This feature has no known activations.