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

    Neuronpedia

    INDEX
    Explanations

    selection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cara
    -0.06
    ملة
    -0.06
    _places
    -0.06
    Disable
    -0.06
     Laundry
    -0.06
    =zeros
    -0.06
     fifo
    -0.06
    riority
    -0.06
     Parish
    -0.06
    $params
    -0.06
    POSITIVE LOGITS
    งต
    0.07
     WHITE
    0.07
     ASF
    0.07
     explain
    0.06
     RESPONSE
    0.06
    ylon
    0.06
     antenn
    0.06
     elegance
    0.06
     depleted
    0.06
     hareket
    0.06
    Act Density 0.006%

    No Known Activations