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

    Neuronpedia

    INDEX
    Explanations

    describing methods/techniques

    np_max-act · gemini-2.0-flash

    This neuron activates on tokens containing the substring “ant.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .dispose
    -0.06
    داد
    -0.06
    กราคม
    -0.06
    _OBJECT
    -0.06
    linkedin
    -0.06
    Accounts
    -0.06
    disposed
    -0.06
    _MANY
    -0.06
     showAlert
    -0.06
    .setToolTipText
    -0.06
    POSITIVE LOGITS
     bar
    0.07
     stuff
    0.07
    -thirds
    0.07
     sorts
    0.07
     quy
    0.06
    영상
    0.06
    �
    0.06
     ord
    0.06
     slices
    0.06
     brut
    0.06
    Act Density 0.007%

    No Known Activations