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

    Neuronpedia

    INDEX
    Explanations

    distancing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cellar
    -0.07
    疗
    -0.07
    카
    -0.07
     tumors
    -0.07
    daemon
    -0.07
     unity
    -0.07
     Leak
    -0.06
     Caucas
    -0.06
    .diff
    -0.06
     Jerusalem
    -0.06
    POSITIVE LOGITS
     MMI
    0.06
    _ERRORS
    0.06
    ازم
    0.06
    Destroy
    0.06
    Fra
    0.06
    roit
    0.06
    ้าร
    0.06
    يط
    0.06
     geçti
    0.06
    нар
    0.06
    Act Density 0.008%

    No Known Activations