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

    Neuronpedia

    INDEX
    Explanations

    sentences about putting things in bags

    oai_token-act-pair · gemini-2.0-flash

    bags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RegressionTest
    -1.09
    IntoConstraints
    -0.78
     архивлан
    -0.78
     '\\;'
    -0.75
    writeFieldEnd
    -0.73
    CppMethod
    -0.67
     Biôgrafia
    -0.65
    aronder
    -0.65
    contentLoaded
    -0.63
     يتيمه
    -0.63
    POSITIVE LOGITS
    Obvious
    0.40
    ❷
    0.39
     Projected
    0.39
     uni
    0.38
    phrodite
    0.37
     Irrelevant
    0.36
     plano
    0.36
    audiovisuel
    0.36
    ukun
    0.36
    written
    0.35
    Act Density 2.000%

    No Known Activations