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

    Neuronpedia

    INDEX
    Explanations

    Paying back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    userdata
    -0.07
    /video
    -0.06
     �
    -0.06
    ��
    -0.06
    ksiyon
    -0.06
    animate
    -0.06
    ervention
    -0.06
     almış
    -0.06
    >())↵
    -0.06
    UTC
    -0.06
    POSITIVE LOGITS
     repay
    0.10
     repayment
    0.08
    isha
    0.07
    PC
    0.07
     rematch
    0.07
     Syntax
    0.07
    Encoded
    0.07
    ombo
    0.06
     zm
    0.06
    unate
    0.06
    Act Density 0.003%

    No Known Activations