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

    Neuronpedia

    INDEX
    Explanations

    slider

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ']*
    -0.07
    _place
    -0.07
    phot
    -0.07
     Arithmetic
    -0.06
    кової
    -0.06
     Prince
    -0.06
    Cell
    -0.06
    qn
    -0.06
     Math
    -0.06
    ;


↵
    -0.06
    POSITIVE LOGITS
     sliders
    0.12
     slider
    0.11
     Slider
    0.10
    Slider
    0.10
    .slider
    0.09
    slider
    0.08
    /slider
    0.08
    -slider
    0.08
     DJ
    0.07
    _slider
    0.07
    Act Density 0.002%

    No Known Activations