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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens representing match scores and related statistical figures.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ılığıyla
    -0.07
     Mec
    -0.07
     Un
    -0.07
     Moz
    -0.07
     //----------------------------------------------------------------
    -0.07
     MetroFramework
    -0.07
    atedRoute
    -0.06
    _CONV
    -0.06
     Workout
    -0.06
     BrowserRouter
    -0.06
    POSITIVE LOGITS
    plain
    0.07
     imag
    0.07
    áž
    0.07
     adult
    0.06
    播放
    0.06
     timing
    0.06
     �
    0.06
     imposs
    0.06
    _disabled
    0.06
    ptions
    0.06
    Act Density 0.001%

    No Known Activations