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

    Neuronpedia

    INDEX
    Explanations

    report releases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conclude
    -0.07
     showcase
    -0.07
     Das
    -0.06
    appear
    -0.06
     mevcut
    -0.06
    ارک
    -0.06
    Central
    -0.06
    _completed
    -0.06
    agnitude
    -0.06
     glucose
    -0.06
    POSITIVE LOGITS
    .ModelAdmin
    0.07
    _beam
    0.06
     rosa
    0.06
     huy
    0.06
    =headers
    0.06
    )",
    0.06
     <%
    0.06
    	cm
    0.06
     REQUEST
    0.06
    ]+"
    0.06
    Act Density 0.077%

    No Known Activations