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

    Neuronpedia

    INDEX
    Explanations

    loader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    W
    -0.06
     ZZ
    -0.06
    ividad
    -0.06
     embroid
    -0.06
    [top
    -0.06
     space
    -0.06
     �
    -0.06
     organization
    -0.06
    .texture
    -0.06
     UNS
    -0.06
    POSITIVE LOGITS
    REDIT
    0.08
    contin
    0.08
    _goods
    0.07
    ]--;↵
    0.07
    اصر
    0.07
     hotelu
    0.07
     eğit
    0.07
     Rifle
    0.06
     baker
    0.06
    "...
    0.06
    Act Density 0.001%

    No Known Activations