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

    Neuronpedia

    INDEX
    Explanations

    academic-style verbs and other words used in publications

    oai_token-act-pair · gemini-2.0-flash

    verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.38
    XmlAccessType
    -0.62
    клопе
    -0.57
    Cor
    -0.57
     Cor
    -0.57
     was
    -0.54
     is
    -0.54
    inação
    -0.51
    belongsTo
    -0.51
    dymyr
    -0.50
    POSITIVE LOGITS
    acular
    0.55
    WithIdentifier
    0.53
     serem
    0.51
    bewerken
    0.51
     refractive
    0.50
     Obed
    0.49
     voegen
    0.48
     yourselves
    0.47
    DebuggerNonUser
    0.47
     mandible
    0.47
    Act Density 1.810%

    No Known Activations