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

    Neuronpedia

    INDEX
    Explanations

    Love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Contracts
    -0.08
    焉
    -0.07
    Once
    -0.07
     pago
    -0.07
    ourt
    -0.07
    благо
    -0.07
     rack
    -0.07
     nº
    -0.06
    OOT
    -0.06
     Diego
    -0.06
    POSITIVE LOGITS
    有能力
    0.08
    �
    0.07
     residential
    0.07
     chilling
    0.07
    鲫
    0.07
    都可以
    0.07
    味道
    0.07
     мужчин
    0.07
    _THREADS
    0.07
    أهل
    0.07
    Act Density 0.052%

    No Known Activations