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

    Neuronpedia

    INDEX
    Explanations

    let

    np_max-act · gemini-2.0-flash

    This neuron specifically detects occurrences of the verb “let.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     найбільш
    -0.08
     Romania
    -0.07
     گردید
    -0.07
     overrun
    -0.07
    uye
    -0.07
    .BindingSource
    -0.07
    .getUser
    -0.07
    аки
    -0.06
     et
    -0.06
    入れ
    -0.06
    POSITIVE LOGITS
     audition
    0.07
    stacle
    0.07
     Petersburg
    0.06
    DW
    0.06
    ajes
    0.06
    amos
    0.06
    obic
    0.06
    Diagram
    0.06
    69
    0.06
    Vertical
    0.06
    Act Density 0.000%

    No Known Activations