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

    Neuronpedia

    INDEX
    Explanations

    Scientific research terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     वक
    -0.06
    ायत
    -0.06
    习
    -0.06
    клад
    -0.06
     Anxiety
    -0.06
    ญ
    -0.06
     Supported
    -0.06
    아파트
    -0.06
    Initial
    -0.06
     boy
    -0.06
    POSITIVE LOGITS
     aslında
    0.07
     peníze
    0.07
    <l
    0.07
    (HttpContext
    0.07
     respawn
    0.06
     Replica
    0.06
    、↵↵
    0.06
     nederland
    0.06
     assembling
    0.06
    ffb
    0.06
    Act Density 0.152%

    No Known Activations