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

    Neuronpedia

    INDEX
    Explanations

    jump

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect Russian tokens referring to physical performance attributes and actions (e.g. endurance, reaction, speed, jumps) in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    JNI
    -0.07
     Wrap
    -0.07
    ache
    -0.06
     bracelets
    -0.06
     Leak
    -0.06
    ijk
    -0.06
     Mitarbeiter
    -0.06
    ???↵↵
    -0.06
     HttpClientModule
    -0.06
    .fft
    -0.06
    POSITIVE LOGITS
    TexParameteri
    0.07
     avec
    0.07
    awai
    0.07
    елов
    0.07
    有限
    0.06
    ському
    0.06
    (PORT
    0.06
    (script
    0.06
     NOI
    0.06
    ื้
    0.06
    Act Density 0.009%

    No Known Activations