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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Handled
    -0.06
    SqlServer
    -0.06
    ٹ
    -0.06
    들과
    -0.06
     fists
    -0.06
     hled
    -0.06
     safety
    -0.06
     atop
    -0.06
    girl
    -0.06
    ницы
    -0.06
    POSITIVE LOGITS
     hlav
    0.07
     pulumi
    0.07
     PrintWriter
    0.07
    PELL
    0.06
    ULA
    0.06
     nắm
    0.06
    ickt
    0.06
    油
    0.06
     tote
    0.06
    .Controls
    0.06
    Act Density 0.015%

    No Known Activations