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

    Neuronpedia

    INDEX
    Explanations

    ment

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “employment” (and its morphological fragments like “employ”/“ment”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     trick
    -0.08
    292
    -0.08
    23
    -0.08
    22
    -0.07
    2
    -0.07
     decide
    -0.07
    33
    -0.07
    á
    -0.07
     decides
    -0.07
    3
    -0.07
    POSITIVE LOGITS
     employment
    0.12
     Employment
    0.10
    Employ
    0.09
     Employer
    0.09
     Employ
    0.09
     employer
    0.09
     Emmanuel
    0.08
    SPELL
    0.08
    employ
    0.08
    employment
    0.08
    Act Density 0.024%

    No Known Activations