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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bread
    -0.06
     revise
    -0.06
     глуб
    -0.06
    ujícím
    -0.06
    _popup
    -0.06
    -valu
    -0.06
     headquarters
    -0.06
    _mgmt
    -0.06
     synchronous
    -0.06
     iteration
    -0.06
    POSITIVE LOGITS
     �
    0.07
     варто
    0.07
    ΟΔ
    0.07
     Term
    0.06
     "+↵
    0.06
     staveb
    0.06
    183
    0.06
     Conj
    0.06
     ста
    0.06
     EXIT
    0.06
    Act Density 0.047%

    No Known Activations