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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .junit
    -0.07
     NA
    -0.06
     convinc
    -0.06
     TELE
    -0.06
     homo
    -0.06
    SR
    -0.06
    .der
    -0.06
    stations
    -0.06
    _arm
    -0.06
     rhetorical
    -0.06
    POSITIVE LOGITS
    _OWNER
    0.06
    PRICE
    0.06
    افظ
    0.06
     beim
    0.06
     Shelby
    0.06
    anchors
    0.06
     alıp
    0.06
     TBD
    0.06
    oldem
    0.06
    .setAlignment
    0.06
    Act Density 0.017%

    No Known Activations