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

    Neuronpedia

    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rowning
    -0.07
    _hs
    -0.06
    01
    -0.06
    _he
    -0.06
    declar
    -0.06
    graf
    -0.06
     Kou
    -0.06
     slip
    -0.06
    br
    -0.06
    _RS
    -0.06
    POSITIVE LOGITS
    ("\\
    0.07
    ABSPATH
    0.07
    Coords
    0.07
     ){
    0.06
    amphetamine
    0.06
    PACKAGE
    0.06
     Designs
    0.06
    igmoid
    0.06
    anyahu
    0.06
     pork
    0.06
    Act Density 0.008%

    No Known Activations