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

    Neuronpedia

    INDEX
    Explanations

    Code and existence checks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tween
    -0.08
    Expense
    -0.06
     теп
    -0.06
     prendre
    -0.06
    _middle
    -0.06
     pé
    -0.06
     fossils
    -0.06
    投融资
    -0.06
    _New
    -0.06
     Tyson
    -0.06
    POSITIVE LOGITS
    _COMMIT
    0.07
     helped
    0.07
    gems
    0.07
    _emit
    0.07
     #"
    0.06
     Judith
    0.06
    }{$
    0.06
    <<"
    0.06
    牢记
    0.06
    كت
    0.06
    Act Density 0.036%

    No Known Activations