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

    Neuronpedia

    INDEX
    Explanations

    SQL join operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     captain
    -0.08
     soldier
    -0.08
    iology
    -0.07
    /array
    -0.07
    -pl
    -0.07
    ült
    -0.07
     rigor
    -0.07
    ḋ
    -0.07
     kilometres
    -0.07
    (async
    -0.07
    POSITIVE LOGITS
    ENOMEM
    0.08
    ㎟
    0.06
     marital
    0.06
    ۦ
    0.06
    ᐝ
    0.06
    🚼
    0.06
    .compat
    0.06
     Christian
    0.06
    泸州
    0.06
     baseball
    0.06
    Act Density 0.035%

    No Known Activations