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

    Neuronpedia

    INDEX
    Explanations

    layer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interpreted
    -0.06
     manifesto
    -0.06
    _return
    -0.06
    Partition
    -0.06
    ��
    -0.06
    배송
    -0.06
     Antwort
    -0.06
    -license
    -0.06
     (),↵
    -0.06
    现代
    -0.06
    POSITIVE LOGITS
     Lam
    0.07
    _COND
    0.07
    [layer
    0.06
     utilizes
    0.06
    omore
    0.06
     laser
    0.06
     utilizar
    0.06
    ellidos
    0.06
     pkg
    0.06
    urally
    0.06
    Act Density 0.004%

    No Known Activations