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

    Neuronpedia

    INDEX
    Explanations

    Published

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robotics
    -0.08
     плот
    -0.07
    te
    -0.07
    方方面面
    -0.07
    toMatch
    -0.07
    瞫
    -0.07
     Alliance
    -0.07
    硭
    -0.07
    PROP
    -0.07
    -radio
    -0.07
    POSITIVE LOGITS
     JAXB
    0.08
    ày
    0.07
    _SC
    0.07
    /cgi
    0.07
    \C
    0.07
     passages
    0.07
     persec
    0.07
    ゔ
    0.06
    .*(
    0.06
     trunc
    0.06
    Act Density 0.007%

    No Known Activations