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

    Neuronpedia

    INDEX
    Explanations

    meaning

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?p
    -0.07
    *p
    -0.06
    ,p
    -0.06
    blr
    -0.06
    $p
    -0.06
     prudent
    -0.06
    포츠
    -0.06
    ��
    -0.06
     css
    -0.06
     sut
    -0.06
    POSITIVE LOGITS
     acceptance
    0.07
     ')'
    0.07
    _EXTENDED
    0.07
    .Here
    0.07
     مخت
    0.06
    غط
    0.06
     biased
    0.06
    WOOD
    0.06
    ического
    0.06
    _SELECTION
    0.06
    Act Density 0.013%

    No Known Activations