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

    Neuronpedia

    INDEX
    Explanations

    NO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    953
    -0.08
     iktidar
    -0.07
    selectorMethod
    -0.07
    χε
    -0.07
    759
    -0.07
    ıc
    -0.06
    istical
    -0.06
    	continue
    -0.06
    .stringify
    -0.06
     peč
    -0.06
    POSITIVE LOGITS
     кл
    0.06
    laws
    0.06
     abolished
    0.06
    .Protocol
    0.06
     rè
    0.06
    .ul
    0.06
     cryptography
    0.06
    ;


↵
    0.06
    ẹp
    0.06
     Assault
    0.06
    Act Density 0.102%

    No Known Activations