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

    Neuronpedia

    INDEX
    Explanations

    numerical problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Som
    -0.07
    okane
    -0.07
     Cookies
    -0.07
    confirmed
    -0.07
     Cache
    -0.07
     rotor
    -0.07
    .credentials
    -0.07
     Madame
    -0.07
     silence
    -0.06
     dough
    -0.06
    POSITIVE LOGITS
    tern
    0.08
    inear
    0.07
    플
    0.07
    ⌊
    0.07
     מאד
    0.07
    แนว
    0.07
    孛
    0.07
     Weinstein
    0.06
    娱乐平台
    0.06
     least
    0.06
    Act Density 0.034%

    No Known Activations