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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ex
    -0.07
    wen
    -0.07
    watch
    -0.07
    渎
    -0.07
    eth
    -0.06
    枇
    -0.06
     Bran
    -0.06
     bubble
    -0.06
     branch
    -0.06
    orch
    -0.06
    POSITIVE LOGITS
     כתוצאה
    0.07
     האדם
    0.07
    楼房
    0.07
     '<?
    0.07
    _HANDLER
    0.07
    美方
    0.07
     "]
    0.07
    .eq
    0.07
    abh
    0.07
     הגוף
    0.07
    Act Density 0.004%

    No Known Activations