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

    Neuronpedia

    INDEX
    Explanations

    expensive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atif
    -0.08
    "].
    -0.07
    ~↵
    -0.07
     jehož
    -0.07
    \\
    -0.07
    MSC
    -0.07
    '
↵
    -0.07
     McCoy
    -0.06
     UNS
    -0.06
     STREAM
    -0.06
    POSITIVE LOGITS
     Güvenlik
    0.07
    binding
    0.06
    userInfo
    0.06
    .plist
    0.06
    imports
    0.06
    uster
    0.06
    thought
    0.06
    .Template
    0.06
     Chest
    0.06
    .State
    0.06
    Act Density 0.031%

    No Known Activations