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

    Neuronpedia

    INDEX
    Explanations

    W

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    な
    -0.07
     spec
    -0.07
    _socket
    -0.07
    نان
    -0.06
    .Equal
    -0.06
    counter
    -0.06
     اليوم
    -0.06
    ymbol
    -0.06
     nightclub
    -0.06
    iden
    -0.06
    POSITIVE LOGITS
     Flush
    0.07
    ORK
    0.06
    -rich
    0.06
     Frem
    0.06
    .INPUT
    0.06
    腐
    0.06
    resident
    0.06
     prices
    0.06
     consolidation
    0.06
     Window
    0.06
    Act Density 0.001%

    No Known Activations