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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Size
    -0.07
     crisis
    -0.07
     úspě
    -0.07
     Is
    -0.07
     resource
    -0.07
     ISA
    -0.07
     víc
    -0.07
    a
    -0.07
     Do
    -0.07
    28
    -0.07
    POSITIVE LOGITS
     they
    0.16
     They
    0.15
    They
    0.14
     them
    0.14
    they
    0.12
     THEY
    0.10
    .They
    0.10
     Them
    0.10
    —they
    0.10
     their
    0.10
    Act Density 0.319%

    No Known Activations