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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to floating‐point numeric tokens (i.e. numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lil
    -0.07
     LE
    -0.07
    getDate
    -0.06
    _PKT
    -0.06
    	temp
    -0.06
     Ş
    -0.06
    ilia
    -0.06
     Fighters
    -0.06
     UserID
    -0.06
    .IsEmpty
    -0.06
    POSITIVE LOGITS
    它
    0.06
    Recogn
    0.06
     atheist
    0.06
    ●
    0.06
    brain
    0.06
    Slow
    0.06
    permanent
    0.06
    credit
    0.06
    'Brien
    0.05
    prene
    0.05
    Act Density 0.320%

    No Known Activations