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

    Neuronpedia

    INDEX
    Explanations

    words related to providing details and evidence, likely in support of an argument

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     otomatig
    -0.46
    fjspx
    -0.45
    Datuak
    -0.43
    Giving
    -0.39
    })));
    -0.38
     suivants
    -0.37
    mobileqq
    -0.37
     Giving
    -0.37
     HasFactory
    -0.37
    もちゃ
    -0.36
    POSITIVE LOGITS
     names
    0.75
     createState
    0.71
     Names
    0.65
    Names
    0.61
     NAMES
    0.60
     nombres
    0.59
    names
    0.58
     namn
    0.57
     name
    0.56
     details
    0.55
    Act Density 7.309%

    No Known Activations