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

    Neuronpedia

    INDEX
    Explanations

    Building, creating, making something

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on past‐participle (–ed) verb forms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ty
    -0.07
    -for
    -0.07
    “For
    -0.07
    ۰۰
    -0.06
     Policies
    -0.06
    _For
    -0.06
    альним
    -0.06
    _city
    -0.06
    REFIX
    -0.06
    Anthony
    -0.06
    POSITIVE LOGITS
     filmed
    0.08
    _modified
    0.08
     grown
    0.08
     thought
    0.08
     iv
    0.07
    Published
    0.07
     chosen
    0.07
     measured
    0.07
     initiated
    0.07
     defined
    0.07
    Act Density 0.211%

    No Known Activations