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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .remove
    -0.06
    ,$
    -0.06
    (cube
    -0.06
    _Height
    -0.06
     intentions
    -0.06
     classical
    -0.06
    τό
    -0.06
    Entries
    -0.06
     Club
    -0.06
     behaving
    -0.06
    POSITIVE LOGITS
     turno
    0.07
    �
    0.07
     gridBagConstraints
    0.07
    iership
    0.07
    โรค
    0.06
    ivas
    0.06
     �
    0.06
    ैठक
    0.06
     ciz
    0.06
     polished
    0.06
    Act Density 0.150%

    No Known Activations