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

    Neuronpedia

    INDEX
    Explanations

    faces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dirs
    -0.07
     readOnly
    -0.07
     THROUGH
    -0.07
     clips
    -0.06
     ruin
    -0.06
    ooth
    -0.06
    ặt
    -0.06
     rumors
    -0.06
    .invokeLater
    -0.06
    ifting
    -0.06
    POSITIVE LOGITS
     행동
    0.08
    ány
    0.07
     земель
    0.07
    cea
    0.07
    가지
    0.06
     GOT
    0.06
     �
    0.06
     adherence
    0.06
    <pre
    0.06
     Actions
    0.06
    Act Density 0.000%

    No Known Activations