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

    Neuronpedia

    INDEX
    Explanations

    Technical/Formal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FIND
    -0.07
     graves
    -0.06
    sob
    -0.06
    altern
    -0.06
    -header
    -0.06
     أجل
    -0.06
     반
    -0.06
    ��
    -0.06
     slavery
    -0.06
     Lol
    -0.06
    POSITIVE LOGITS
    яж
    0.08
    LOOP
    0.07
    _MA
    0.06
     afirm
    0.06
     Hilton
    0.06
     چیزی
    0.06
    süz
    0.06
     خیابان
    0.06
     reviewer
    0.06
    Arc
    0.06
    Act Density 0.000%

    No Known Activations