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

    Neuronpedia

    INDEX
    Explanations

    Code project setup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urnal
    -0.08
    Jacob
    -0.08
    DDR
    -0.07
    ZT
    -0.07
    무
    -0.07
    들의
    -0.07
     tirar
    -0.07
    odom
    -0.07
    olic
    -0.07
    ורים
    -0.07
    POSITIVE LOGITS
    —for
    0.08
    0.07
     �
    0.07
     جلس
    0.07
    

    0.07
     toget
    0.07
     recherch
    0.07
     alug
    0.07
    .binary
    0.07
     padha
    0.07
    Act Density 0.002%
    No Known Activations