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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     colleagues
    -0.07
     maritime
    -0.06
     desper
    -0.06
     threshold
    -0.06
    ění
    -0.06
     cue
    -0.06
     wagon
    -0.06
     emphasized
    -0.06
     Qu
    -0.06
     tej
    -0.06
    POSITIVE LOGITS
    StartupScript
    0.07
    TestClass
    0.07
    ้บร
    0.06
     έως
    0.06
    ρω
    0.06
    _Pin
    0.06
     수정
    0.06
    ��
    0.06
    Sac
    0.06
     дог
    0.06
    Act Density 0.135%

    No Known Activations