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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _recv
    -0.08
     recebe
    -0.07
    ática
    -0.07
    린
    -0.07
     educação
    -0.07
    奶粉
    -0.07
     king
    -0.06
    Salvar
    -0.06
    acea
    -0.06
     SSC
    -0.06
    POSITIVE LOGITS
    (handle
    0.07
    \$
    0.07
     operand
    0.07
    单
    0.07
    -controlled
    0.07
    �
    0.07
     consult
    0.06
    并
    0.06
    �
    0.06
    �
    0.06
    Act Density 0.107%

    No Known Activations