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

    Neuronpedia

    INDEX
    Explanations

    mentions of heating materials

    oai_token-act-pair · gemini-2.0-flash

    High Temperatures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hot
    -1.63
     heat
    -1.59
     Heat
    -1.43
     hotter
    -1.43
     heating
    -1.42
    Heat
    -1.39
     temperature
    -1.38
     warm
    -1.37
     heated
    -1.37
    hot
    -1.34
    POSITIVE LOGITS
    eridge
    0.50
    quiao
    0.49
    クリート
    0.47
    OrNil
    0.47
    struts
    0.47
    0.46
     propOrder
    0.46
     Trujillo
    0.45
    uyler
    0.45
     רע
    0.45
    Act Density 0.405%

    No Known Activations