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

    Neuronpedia

    INDEX
    Explanations

    state or time abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hait
    -0.07
     Crist
    -0.06
    .DotNetBar
    -0.06
    。今
    -0.06
    render
    -0.06
     Mim
    -0.06
    итив
    -0.06
    charted
    -0.06
    یری
    -0.06
    _Description
    -0.06
    POSITIVE LOGITS
     California
    0.08
     mutual
    0.08
     realise
    0.07
     Padres
    0.07
     kernels
    0.06
     trusted
    0.06
    _contains
    0.06
    [G
    0.06
     Diego
    0.06
    /local
    0.06
    Act Density 0.264%

    No Known Activations