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

    Neuronpedia

    INDEX
    Explanations

    expand text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intersection
    -0.08
     cle
    -0.08
     Mathieu
    -0.07
    _usb
    -0.07
    _prec
    -0.07
     û
    -0.07
     swift
    -0.07
     Hel
    -0.07
     atl
    -0.07
     streamlined
    -0.07
    POSITIVE LOGITS
    扩
    0.12
     uitbre
    0.11
     expands
    0.11
     verläng
    0.11
    増
    0.11
    扩大
    0.10
     expansions
    0.10
     Expand
    0.10
     расшир
    0.10
     увеличить
    0.10
    Act Density 0.007%

    No Known Activations