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

    Neuronpedia

    INDEX
    Explanations

    research findings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lain
    -0.06
    ーニ
    -0.06
    descr
    -0.06
    CHA
    -0.06
     Funny
    -0.06
    �
    -0.06
    _cert
    -0.06
     Modes
    -0.06
     Territory
    -0.06
    departments
    -0.06
    POSITIVE LOGITS
    ربية
    0.07
     preseason
    0.07
     �
    0.07
     хорош
    0.07
    ">
↵
    0.06
    �
    0.06
    แหล
    0.06
     ech
    0.06
    산
    0.06
    _tensor
    0.06
    Act Density 0.104%

    No Known Activations