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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find decimal fractions in numeric data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     >&
    -0.07
    вит
    -0.06
    реть
    -0.06
     Director
    -0.06
    itter
    -0.06
     клад
    -0.06
    .:.:
    -0.06
    crear
    -0.06
     فال
    -0.06
     Splash
    -0.06
    POSITIVE LOGITS
    Route
    0.07
    ho
    0.07
    ------------------------------
    0.06
     života
    0.06
    �
    0.06
     MICRO
    0.06
     MPC
    0.06
    οκ
    0.06
     molecule
    0.06
    ิทธ
    0.06
    Act Density 0.003%

    No Known Activations