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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     towering
    -0.06
    ocê
    -0.06
    Signing
    -0.06
    Ơ
    -0.06
    ôt
    -0.06
    andscape
    -0.06
    刻
    -0.06
    κα
    -0.06
    کاران
    -0.06
     рей
    -0.06
    POSITIVE LOGITS
    (),'
    0.07
    _HW
    0.07
     yıllarda
    0.06
     التق
    0.06
    _ids
    0.06
    TabIndex
    0.06
     신입
    0.06
    ,target
    0.06
     Nicolas
    0.06
    =".$_
    0.06
    Act Density 0.000%

    No Known Activations