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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron fires on the standalone token “to,” i.e. the infinitive marker (especially in “about to” or similar constructions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     strengthened
    -0.06
    _coeff
    -0.06
    ようです
    -0.06
     samostat
    -0.06
    _hard
    -0.06
     merkez
    -0.06
     detta
    -0.06
     nucleus
    -0.06
    �
    -0.06
    Everything
    -0.06
    POSITIVE LOGITS
     Waiting
    0.07
     малень
    0.07
     ",
    0.06
    拟
    0.06
    .dir
    0.06
     constitutes
    0.06
     waiting
    0.06
     刘
    0.06
     방송
    0.06
    λο
    0.06
    Act Density 0.009%

    No Known Activations