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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Prot
    -0.07
     node
    -0.07
    TE
    -0.07
    户籍
    -0.07
     одного
    -0.07
    웹
    -0.07
     domic
    -0.07
    /boot
    -0.07
    _cat
    -0.07
    ipheral
    -0.07
    POSITIVE LOGITS
    Has
    0.08
    Additionally
    0.07
    'am
    0.07
     promises
    0.07
    焰
    0.07
     chicas
    0.06
     admissions
    0.06
    一如既往
    0.06
    댐
    0.06
     Unused
    0.06
    Act Density 0.123%

    No Known Activations