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

    Neuronpedia

    INDEX
    Explanations

    Memory/data organization

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing fractional values (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     artery
    -0.07
     IPS
    -0.06
    ęż
    -0.06
     iss
    -0.06
     посл
    -0.06
    patients
    -0.06
    iset
    -0.06
     capture
    -0.06
     JNI
    -0.06
     urinary
    -0.06
    POSITIVE LOGITS
    ）:
    0.06
    -induced
    0.06
    onomic
    0.06
    -packed
    0.06
    .hashCode
    0.06
     halves
    0.06
    	ac
    0.06
     كور
    0.06
     dří
    0.06
    cción
    0.06
    Act Density 0.061%

    No Known Activations