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

    Neuronpedia

    INDEX
    Explanations

    cond

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the technical term “condenser.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Kirk
    -0.08
     areas
    -0.07
    727
    -0.07
     stepping
    -0.07
     tactic
    -0.07
     West
    -0.07
     Arabian
    -0.07
     allegiance
    -0.07
    York
    -0.07
     trek
    -0.07
    POSITIVE LOGITS
     cond
    0.08
     condol
    0.08
    cond
    0.08
    madı
    0.08
    �
    0.08
     condemned
    0.07
    odo
    0.07
    �
    0.07
     condensed
    0.07
    boa
    0.07
    Act Density 0.014%

    No Known Activations