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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric tokens that represent floating-point values (i.e. numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ACHE
    -0.07
     aggress
    -0.06
     CONTACT
    -0.06
    isations
    -0.06
    Ly
    -0.06
     Cros
    -0.06
     specular
    -0.06
    ôm
    -0.06
    .pictureBox
    -0.06
    ovan
    -0.06
    POSITIVE LOGITS
    、​
    0.07
    .removeFrom
    0.07
    Buying
    0.06
     setFrame
    0.06
    "context
    0.06
     dlou
    0.06
     amazed
    0.06
    대비
    0.06
     Savaşı
    0.06
    />
↵
    0.06
    Act Density 0.015%

    No Known Activations