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

    Neuronpedia

    INDEX
    Explanations

    ears

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الاخ
    -0.06
    ("---
    -0.06
    <pre
    -0.06
     ακ
    -0.06
    (instruction
    -0.06
    凌
    -0.06
    ustomer
    -0.06
    dirty
    -0.06
     described
    -0.06
     drawers
    -0.06
    POSITIVE LOGITS
    断
    0.07
    前の
    0.07
     Nam
    0.07
    OTH
    0.06
     cosy
    0.06
    .J
    0.06
    uger
    0.06
     EB
    0.06
    км
    0.06
     Gör
    0.06
    Act Density 0.000%

    No Known Activations