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

    Neuronpedia

    INDEX
    Explanations

    stories, fanfiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     occup
    -0.07
    ụy
    -0.07
     alto
    -0.07
     fetal
    -0.07
    混
    -0.07
     Ald
    -0.06
     villains
    -0.06
    leftrightarrow
    -0.06
    نین
    -0.06
     cold
    -0.06
    POSITIVE LOGITS
     hackers
    0.07
    impan
    0.06
    'action
    0.06
    Doing
    0.06
     الجم
    0.06
    ระด
    0.06
     seria
    0.06
     дж
    0.06
    (UnityEngine
    0.06
    _campaign
    0.06
    Act Density 0.233%

    No Known Activations