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

    Neuronpedia

    INDEX
    Explanations

    asking for or offering help

    np_max-act · gemini-2.0-flash

    The neuron activates on Portuguese infinitive verbs ending in “-ar.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     homogeneous
    -0.06
    -containing
    -0.06
    uido
    -0.06
    ины
    -0.06
    .dsl
    -0.06
    ニニ
    -0.06
    enarios
    -0.06
    _ab
    -0.06
    iny
    -0.06
    _GRID
    -0.06
    POSITIVE LOGITS
    帮助
    0.07
    :])↵
    0.07
     job
    0.07
    ,value
    0.07
     handy
    0.07
    -position
    0.06
    益
    0.06
     Rosenstein
    0.06
    assen
    0.06
     özel
    0.06
    Act Density 0.013%

    No Known Activations