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

    Neuronpedia

    INDEX
    Explanations

    words associated with scientific findings of different qualities

    oai_token-act-pair · gemini-2.0-flash

    high

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.66
    TagMode
    -0.58
    
    -0.57
    Personendaten
    -0.56
    BeginContext
    -0.52
    lgari
    -0.52
    !*\
    -0.51
    EndContext
    -0.51
    pulumi
    -0.51
    stdc
    -0.50
    POSITIVE LOGITS
    RouterModule
    0.56
     Secondly
    0.56
    LocationManager
    0.56
     poorer
    0.55
    harusnya
    0.54
     firstly
    0.53
     roche
    0.52
     좋
    0.52
    abstractmethod
    0.52
     poor
    0.52
    Act Density 0.760%

    No Known Activations