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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     event
    -0.07
    也有
    -0.07
     intervene
    -0.06
    ��
    -0.06
    {})
    -0.06
    )+(
    -0.06
    ARATION
    -0.06
    cleanup
    -0.06
    endant
    -0.06
    <num
    -0.06
    POSITIVE LOGITS
    стра
    0.07
    (Me
    0.07
    This
    0.07
    (".
    0.07
     this
    0.06
    this
    0.06
    .Av
    0.06
    ping
    0.06
    (pass
    0.06
     "...
    0.06
    Act Density 0.042%

    No Known Activations