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

    Neuronpedia

    INDEX
    Explanations

    Find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     useRef
    -0.07
    онів
    -0.07
    اهای
    -0.06
     constitution
    -0.06
     BET
    -0.06
     tố
    -0.06
    '),
↵
    -0.06
     Fransa
    -0.06
    .Mockito
    -0.06
    цями
    -0.06
    POSITIVE LOGITS
     shields
    0.07
    /tr
    0.06
     assign
    0.06
    [top
    0.06
    _gen
    0.06
     Vertex
    0.06
     jug
    0.06
     calendar
    0.06
     인
    0.06
    ür
    0.06
    Act Density 0.000%

    No Known Activations