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

    Neuronpedia

    INDEX
    Explanations

    medical alterations/dysfunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (*)
    -0.08
     grads
    -0.07
    major
    -0.07
    werk
    -0.07
    究竟是
    -0.07
    满满
    -0.07
     intuition
    -0.07
    never
    -0.07
    ⭑
    -0.07
     kids
    -0.07
    POSITIVE LOGITS
    ようになった
    0.07
     rãi
    0.07
     Play
    0.06
     развит
    0.06
    �
    0.06
     أغسطس
    0.06
     להביא
    0.06
    垩
    0.06
     mell
    0.06
     Assy
    0.06
    Act Density 0.040%

    No Known Activations