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

    Neuronpedia

    INDEX
    Explanations

    activism

    np_max-act · gemini-2.0-flash

    This neuron detects persuasive calls to action—second-person “you” imperatives urging the reader to do something (e.g., buy, commit, request).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    kiye
    -0.07
    ël
    -0.06
     limb
    -0.06
    erra
    -0.06
    _PASSWORD
    -0.06
    Manchester
    -0.06
    loop
    -0.06
    logg
    -0.06
    lp
    -0.06
     Manchester
    -0.06
    POSITIVE LOGITS
     müc
    0.08
     �
    0.08
    輪
    0.07
     geological
    0.07
     chlorine
    0.07
     것을
    0.06
     darken
    0.06
    munition
    0.06
    .lista
    0.06
     داستان
    0.06
    Act Density 0.041%

    No Known Activations