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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     la
    -0.07
     y
    -0.07
    _size
    -0.06
    ansas
    -0.06
     alloc
    -0.06
     mue
    -0.06
     viagra
    -0.06
    >P
    -0.06
    _bias
    -0.06
     ik
    -0.06
    POSITIVE LOGITS
    etSocketAddress
    0.07
     �
    0.07
    аза
    0.07
    ViewPager
    0.07
    Explanation
    0.07
     Δή
    0.06
    _REPO
    0.06
    DOCTYPE
    0.06
    शन
    0.06
     हमल
    0.06
    Act Density 0.735%

    No Known Activations