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

    Neuronpedia

    INDEX
    Explanations

    small numbers acting as adjectives and words related to companies or organizations

    oai_token-act-pair · gemini-2.0-flash

    Company/Organization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hiers
    -0.47
    ivore
    -0.46
    ipfel
    -0.43
    MockMvc
    -0.40
    okok
    -0.40
    TaskId
    -0.39
    @(
    -0.38
     tarea
    -0.38
     agré
    -0.38
    edoc
    -0.37
    POSITIVE LOGITS
     company
    1.41
     companies
    1.19
    company
    1.11
     organization
    1.11
     organisation
    1.06
     Company
    1.00
    Company
    1.00
     bedrijf
    1.00
     agency
    0.99
     perusahaan
    0.97
    Act Density 1.098%

    No Known Activations