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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Slate
    -0.07
    LOWER
    -0.06
    -pressure
    -0.06
     blunt
    -0.06
    -middle
    -0.06
    Sigma
    -0.06
    adt
    -0.06
     imagem
    -0.06
    Extreme
    -0.06
    _Update
    -0.06
    POSITIVE LOGITS
    _bw
    0.07
     Univers
    0.07
     Dış
    0.07
     
↵ 
↵
    0.06
    /projects
    0.06
    ardu
    0.06
     urč
    0.06
    -dashboard
    0.06
    �
    0.06
    唯一
    0.06
    Act Density 0.008%

    No Known Activations