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

    Neuronpedia

    INDEX
    Explanations

    dependent

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens related to “depend,” i.e. words or morphemes expressing dependence (e.g. depend, dependent, dependency).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Carlton
    -0.07
    uzz
    -0.07
    RA
    -0.07
    Roll
    -0.07
    Color
    -0.07
     vua
    -0.07
    �
    -0.07
     TX
    -0.07
     sco
    -0.06
     rfl
    -0.06
    POSITIVE LOGITS
     dependent
    0.13
    -dependent
    0.10
     Dep
    0.09
    Dep
    0.09
    pend
    0.08
    PEND
    0.08
    .dep
    0.08
     depend
    0.08
     dependence
    0.08
     Depend
    0.08
    Act Density 0.019%

    No Known Activations