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

    Neuronpedia

    INDEX
    Explanations

    teasing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    粉
    -0.07
    芬
    -0.07
     controlId
    -0.06
     juga
    -0.06
    @Override
    -0.06
     frustration
    -0.06
     gin
    -0.06
    Autowired
    -0.06
    ��
    -0.06
    atan
    -0.06
    POSITIVE LOGITS
     worksheets
    0.07
     annihil
    0.07
    igrated
    0.06
    werp
    0.06
    lector
    0.06
    ridge
    0.06
    66
    0.06
    oser
    0.06
     etmeye
    0.06
    'clock
    0.06
    Act Density 0.041%

    No Known Activations