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

    Neuronpedia

    INDEX
    Explanations

    DEF

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eh
    -0.07
    蹴
    -0.07
     TOD
    -0.07
    ㈎
    -0.07
     ADDRESS
    -0.06
     Otto
    -0.06
     Mack
    -0.06
    飞船
    -0.06
    춘
    -0.06
    NK
    -0.06
    POSITIVE LOGITS
     adversity
    0.08
    aturing
    0.08
    /pr
    0.08
    🌅
    0.08
    \Template
    0.07
    เพศ
    0.07
    感人
    0.07
    Profile
    0.07
    "_
    0.07
    쁜
    0.07
    Act Density 0.000%

    No Known Activations