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

    Neuronpedia

    INDEX
    Explanations

    trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ूं
    -0.06
    _tree
    -0.06
     한다
    -0.06
    アニメ
    -0.06
     BRA
    -0.06
    ์ว
    -0.06
    ्ष
    -0.06
     Thumbnail
    -0.05
     keeping
    -0.05
    brids
    -0.05
    POSITIVE LOGITS
    <section
    0.08
    ="$(
    0.07
    υμ
    0.06
     Cas
    0.06
     strengthening
    0.06
    -ticket
    0.06
     certifications
    0.06
     prostitut
    0.06
    TestId
    0.06
    	cc
    0.06
    Act Density 0.018%

    No Known Activations