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

    Neuronpedia

    INDEX
    Explanations

    average

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    forming
    -0.07
     loft
    -0.06
     legal
    -0.06
     эффектив
    -0.06
    imus
    -0.06
    可能
    -0.06
     영화
    -0.06
     bowling
    -0.06
    eth
    -0.06
     sake
    -0.06
    POSITIVE LOGITS
    '=
    0.07
    ωμα
    0.06
    =n
    0.06
    0.06
    .dsl
    0.06
    ็็
    0.06
    _Red
    0.06
     ){↵↵
    0.06
     Minority
    0.06
    ленный
    0.06
    Act Density 0.036%

    No Known Activations