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

    Neuronpedia

    INDEX
    Explanations

    perplex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propriet
    -0.07
     ASF
    -0.07
    uart
    -0.07
     Composite
    -0.07
    Combined
    -0.07
     Width
    -0.07
     Combined
    -0.06
    spinner
    -0.06
     Поэтому
    -0.06
     obrov
    -0.06
    POSITIVE LOGITS
     perception
    0.07
     bankruptcy
    0.07
    .Try
    0.07
    Watch
    0.06
     melting
    0.06
     schizophrenia
    0.06
    ourke
    0.06
     envisioned
    0.06
     (_,
    0.06
     نج
    0.06
    Act Density 0.007%

    No Known Activations