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

    Neuronpedia

    INDEX
    Explanations

    population disparities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Block
    -0.07
     Wired
    -0.07
    之前
    -0.07
     minister
    -0.06
     borrowers
    -0.06
    _eye
    -0.06
    -0.06
     bleiben
    -0.06
    Government
    -0.06
     resources
    -0.06
    POSITIVE LOGITS
     �
    0.07
    \Storage
    0.06
     bara
    0.06
    Lf
    0.06
    ={↵
    0.06
    .Appearance
    0.06
     servi
    0.06
     naopak
    0.06
     rw
    0.06
    .PL
    0.06
    Act Density 0.062%

    No Known Activations