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

    Neuronpedia

    INDEX
    Explanations

    many-to-many relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _origin
    -0.07
    	success
    -0.06
    Vin
    -0.06
     iss
    -0.06
     FF
    -0.06
     getResult
    -0.06
     Sham
    -0.06
    .fromRGBO
    -0.06
     rov
    -0.06
    stringValue
    -0.06
    POSITIVE LOGITS
     discarded
    0.06
    под
    0.06
    udp
    0.06
     jumps
    0.06
     stri
    0.06
     Nothing
    0.06
     Wants
    0.06
     tarım
    0.06
     diyor
    0.06
    agog
    0.06
    Act Density 0.101%

    No Known Activations