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
     enquiry
    -0.07
    _size
    -0.06
    ា�
    -0.06
    quiry
    -0.06
    68
    -0.06
    HANDLE
    -0.06
    ized
    -0.06
    fd
    -0.06
    Streaming
    -0.06
     ++$
    -0.06
    POSITIVE LOGITS
     transforms
    0.07
    XXXX
    0.06
    .chapter
    0.06
     compra
    0.06
    шается
    0.06
    .generated
    0.06
    alardan
    0.06
    uitar
    0.06
     пят
    0.06
     darüber
    0.06
    Act Density 0.035%

    No Known Activations