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

    Neuronpedia

    INDEX
    Explanations

    Declaration of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StringEncoding
    -0.07
    Russia
    -0.07
    ureau
    -0.07
    icamente
    -0.07
    _MOV
    -0.07
     Enforcement
    -0.07
     questi
    -0.06
     Lod
    -0.06
    -images
    -0.06
     __________________↵↵
    -0.06
    POSITIVE LOGITS
     Declaration
    0.08
     declaration
    0.07
     devez
    0.06
    Right
    0.06
    /nav
    0.06
     vow
    0.06
    -cookie
    0.06
     normal
    0.06
     echang
    0.05
    -mf
    0.05
    Act Density 0.000%

    No Known Activations