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

    Neuronpedia

    INDEX
    Explanations

    globe

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the token “globe” (especially the proper-name form “Globe”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     shear
    -0.08
     Ahmed
    -0.07
     tearing
    -0.07
     Sales
    -0.07
    ITICAL
    -0.07
     engr
    -0.07
     suicidal
    -0.07
     marsh
    -0.06
    Wei
    -0.06
    Jar
    -0.06
    POSITIVE LOGITS
    glob
    0.10
     globe
    0.10
     glob
    0.09
     Globe
    0.09
    .glob
    0.08
     Glob
    0.08
    156
    0.07
     hlavou
    0.07
    cope
    0.07
     několika
    0.07
    Act Density 0.004%

    No Known Activations