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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     λ
    -0.08
     targets
    -0.07
    𝐋
    -0.07
    ￄ
    -0.07
    ♊
    -0.07
    @Autowired
    -0.06
    lam
    -0.06
     Julia
    -0.06
    łożyć
    -0.06
    ถาม
    -0.06
    POSITIVE LOGITS
    riad
    0.07
    _PER
    0.07
    recht
    0.07
    干线
    0.07
    _rank
    0.07
    fk
    0.07
    charg
    0.07
    此项
    0.07
    (INT
    0.07
    _report
    0.07
    Act Density 0.001%

    No Known Activations