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

    Neuronpedia

    INDEX
    Explanations

    internet infrastructure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PU
    -0.07
    :
↵
↵
    -0.07
    other
    -0.06
    ination
    -0.06
    писок
    -0.06
     第一
    -0.06
    男人
    -0.06
    ğin
    -0.06
    引
    -0.06
     Coal
    -0.06
    POSITIVE LOGITS
     تص
    0.07
     descent
    0.06
    /plain
    0.06
     >&
    0.06
    死
    0.05
    طل
    0.05
     Illustrated
    0.05
     ust
    0.05
     căn
    0.05
     geme
    0.05
    Act Density 0.075%

    No Known Activations