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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HEN
    -0.07
     XR
    -0.07
    /home
    -0.07
    -speaking
    -0.07
    たちは
    -0.06
     PASSWORD
    -0.06
    post
    -0.06
     legitimate
    -0.06
     defeated
    -0.06
     خارجی
    -0.06
    POSITIVE LOGITS
     nutrit
    0.07
    _ESCAPE
    0.06
     APS
    0.06
     microbi
    0.06
    <Renderer
    0.06
    Caps
    0.06
     leurs
    0.06
    (UINT
    0.06
    rock
    0.06
    EGA
    0.06
    Act Density 0.007%

    No Known Activations