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

    Neuronpedia

    INDEX
    Explanations

    credential

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拾
    -0.07
    たく
    -0.07
    AAAA
    -0.07
    𝑅
    -0.06
     fals
    -0.06
     о
    -0.06
     art
    -0.06
    ⼟
    -0.06
    破
    -0.06
    -body
    -0.06
    POSITIVE LOGITS
     STDMETHOD
    0.07
    밍
    0.07
    typeof
    0.07
    utsche
    0.07
    shader
    0.07
     caveat
    0.07
     registrations
    0.07
    ******
↵
    0.07
     Audience
    0.07
    classmethod
    0.07
    Act Density 0.004%

    No Known Activations