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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    に対
    -0.07
     resilience
    -0.06
     Qed
    -0.06
    ilo
    -0.06
    ocado
    -0.06
    -du
    -0.06
     نزد
    -0.06
     Ты
    -0.06
     이어
    -0.06
    imas
    -0.06
    POSITIVE LOGITS
     Kore
    0.06
     erotici
    0.06
    ,.
    0.06
    (Message
    0.06
     olab
    0.06
    Processing
    0.06
    podob
    0.06
     quotations
    0.06
    iVar
    0.06
    ดำ
    0.06
    Act Density 0.194%

    No Known Activations