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

    Neuronpedia

    INDEX
    Explanations

    bas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
                ↵
    -0.07
    -visible
    -0.06
            ↵
    -0.06
     průběhu
    -0.06
    _PARAMETER
    -0.06
    
    -0.06
    _CRE
    -0.06
    .posts
    -0.06
    ibus
    -0.06
     стор
    -0.06
    POSITIVE LOGITS
     Falcon
    0.07
     Olivia
    0.06
    (bean
    0.06
    ons
    0.06
    ,omitempty
    0.06
     里
    0.06
    (color
    0.06
    (false
    0.06
    Bat
    0.06
     Alonso
    0.06
    Act Density 0.089%

    No Known Activations