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

    Neuronpedia

    INDEX
    Explanations

    tangled mess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mView
    -0.08
    ра�
    -0.07
    Trivia
    -0.07
    לנד
    -0.07
    贾
    -0.07
     bif
    -0.07
    eresa
    -0.07
    ën
    -0.06
    être
    -0.06
    employee
    -0.06
    POSITIVE LOGITS
    烀
    0.07
    XC
    0.07
    ختص
    0.07
     understanding
    0.07
     understands
    0.07
    .Lines
    0.07
    .loaded
    0.07
     struggles
    0.07
    אפל
    0.07
    Default
    0.06
    Act Density 0.035%

    No Known Activations