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

    Neuronpedia

    INDEX
    Explanations

    choose

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the prompt word “Choose,” i.e. when a text is asking the user to select or pick something.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     remnants
    -0.08
     Petr
    -0.08
    amat
    -0.07
     �
    -0.07
     mitt
    -0.07
    land
    -0.07
     barn
    -0.07
     packs
    -0.07
     Bath
    -0.07
    art
    -0.06
    POSITIVE LOGITS
     chosen
    0.12
     choose
    0.12
     choosing
    0.10
    chosen
    0.10
    .choose
    0.10
     choice
    0.10
    .choices
    0.09
     Choice
    0.09
     Choose
    0.08
    choice
    0.08
    Act Density 0.040%

    No Known Activations