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

    Neuronpedia

    INDEX
    Explanations

    Software code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ވ
    -0.08
    .MESSAGE
    -0.07
     Bl
    -0.07
     אברה
    -0.06
     Apprent
    -0.06
     specular
    -0.06
    �
    -0.06
    lsru
    -0.06
    )^
    -0.06
    >x
    -0.06
    POSITIVE LOGITS
    搬运
    0.07
    ทย
    0.07
    ↵    ↵    ↵
    0.07
    IMATION
    0.07
    $(
    0.07
    パターン
    0.06
    .sin
    0.06
     ])↵
    0.06
     Remarks
    0.06
     velocities
    0.06
    Act Density 0.000%

    No Known Activations