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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes

    np_max-act · gemini-2.0-flash

    This neuron detects CIDR-style subnet notations (a slash “/” followed by a numeric prefix length) in IP address expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     baiser
    -0.06
     Beer
    -0.06
    sis
    -0.06
    cio
    -0.06
     внутріш
    -0.06
    _gradient
    -0.06
    лерг
    -0.06
    _instance
    -0.06
    _prev
    -0.06
     fj
    -0.06
    POSITIVE LOGITS
     Conscious
    0.07
     junge
    0.07
     mia
    0.06
     Jamaica
    0.06
    )}>↵
    0.06
    ookie
    0.06
     就
    0.06
     incontr
    0.06
    .artist
    0.06
     Toastr
    0.06
    Act Density 0.035%

    No Known Activations