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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reunited
    -0.07
    _WRAP
    -0.07
     Conference
    -0.06
     kterého
    -0.06
     inequalities
    -0.06
     showdown
    -0.06
     Marathon
    -0.06
     towers
    -0.06
    这个
    -0.06
    ospel
    -0.06
    POSITIVE LOGITS
     […
    0.07
    .Kind
    0.06
    certificate
    0.06
     acknowledging
    0.06
     vandal
    0.06
    .row
    0.06
    الد
    0.06
    .Migrations
    0.06
    .ex
    0.06
    ponses
    0.06
    Act Density 0.002%

    No Known Activations