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

    Neuronpedia

    INDEX
    Explanations

    oid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (act
    -0.07
     설치
    -0.06
     alike
    -0.06
     urn
    -0.06
    pst
    -0.06
    <input
    -0.06
    release
    -0.06
    登場
    -0.06
     Boris
    -0.06
    리의
    -0.06
    POSITIVE LOGITS
    _transient
    0.08
    ंपर
    0.07
     akadem
    0.06
     FIRE
    0.06
    nowled
    0.06
    ΗΜΑ
    0.06
    amines
    0.06
    :")↵
    0.06
    iquid
    0.06
    AGO
    0.06
    Act Density 0.002%

    No Known Activations