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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rodu
    -0.06
    Americans
    -0.06
     Mej
    -0.06
    ’є
    -0.06
     unlucky
    -0.06
    HW
    -0.06
    .eql
    -0.06
     cautioned
    -0.06
     nieu
    -0.06
    relevant
    -0.06
    POSITIVE LOGITS
    +"_
    0.07
    Seek
    0.07
     Publications
    0.07
     sayı
    0.06
    如
    0.06
     to
    0.06
     collected
    0.06
    �
    0.06
    .headers
    0.06
    یشه
    0.06
    Act Density 0.009%

    No Known Activations