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

    Neuronpedia

    INDEX
    Explanations

    Licensing boilerplate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Rotate
    -0.08
    ⌀
    -0.07
     Coch
    -0.07
    放松
    -0.07
    🖖
    -0.07
    ↵            
↵
    -0.07
     â
    -0.07
    ())).
    -0.07
    oints
    -0.07
    irth
    -0.07
    POSITIVE LOGITS
    Liverpool
    0.08
     vem
    0.07
    fb
    0.07
     Enrollment
    0.07
    ktion
    0.06
    NG
    0.06
    rail
    0.06
     Md
    0.06
     Restrictions
    0.06
    مطلوب
    0.06
    Act Density 0.003%

    No Known Activations