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

    Neuronpedia

    INDEX
    Explanations

    code data, symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emotions
    -0.06
    fabric
    -0.06
    材
    -0.06
     Internal
    -0.06
     domest
    -0.06
    changer
    -0.06
    aval
    -0.06
     congratulate
    -0.06
    -Headers
    -0.06
     دارد
    -0.06
    POSITIVE LOGITS
    [NUM
    0.07
    ắc
    0.07
    ="'+
    0.07
     hå
    0.06
    ('.',
    0.06
     [...
    0.06
    igh
    0.06
    −
    0.06
    .+
    0.06
     희
    0.06
    Act Density 0.103%

    No Known Activations