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

    Neuronpedia

    INDEX
    Explanations

    remove

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sco
    -0.07
    JSImport
    -0.07
     Honor
    -0.07
    avadoc
    -0.07
     Pros
    -0.06
    targets
    -0.06
     Artificial
    -0.06
     tester
    -0.06
     ves
    -0.06
     Heavy
    -0.06
    POSITIVE LOGITS
     있도록
    0.08
    制度
    0.07
     Mostly
    0.07
    _FIELDS
    0.06
     зміст
    0.06
     Scalia
    0.06
    LETE
    0.06
     때문에
    0.06
    _SCHEMA
    0.06
    _modal
    0.06
    Act Density 0.001%

    No Known Activations