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

    Neuronpedia

    INDEX
    Explanations

    BE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Old
    -0.07
     harming
    -0.07
    mites
    -0.06
    INSTALL
    -0.06
     těch
    -0.06
     kısm
    -0.06
     Deaths
    -0.06
    letters
    -0.06
     vont
    -0.06
    .target
    -0.06
    POSITIVE LOGITS
     infinity
    0.07
     createDate
    0.06
    immer
    0.06
    ......↵↵
    0.06
    웨
    0.06
    αιο
    0.06
    �
    0.06
     сон
    0.05
     Ply
    0.05
     شرق
    0.05
    Act Density 0.001%

    No Known Activations