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

    Neuronpedia

    INDEX
    Explanations

    Almora and Nagano places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     work
    -0.07
    �
    -0.07
    รวด
    -0.07
    .Word
    -0.07
    inea
    -0.07
    四川
    -0.07
    _DETAIL
    -0.07
    Computer
    -0.06
     mơ
    -0.06
    דווח
    -0.06
    POSITIVE LOGITS
     scm
    0.09
    odom
    0.07
     Ot
    0.07
     regulations
    0.07
     fh
    0.07
     Эт
    0.07
    asad
    0.07
     Doom
    0.07
    痛点
    0.07
     CEL
    0.07
    Act Density 0.134%

    No Known Activations