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

    Neuronpedia

    INDEX
    Explanations

    words and phrases from police or court reports about a crime.

    oai_token-act-pair · gemini-2.0-flash

    Legal/crime related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.65
    windowFixed
    -0.64
    LookAnd
    -0.62
     дописавши
    -0.56
    genstein
    -0.52
     Volks
    -0.52
    ImageContext
    -0.50
    sproble
    -0.50
    Хьажоргаш
    -0.48
     TPS
    -0.47
    POSITIVE LOGITS
    лючение
    0.60
    исленность
    0.60
    Tracce
    0.56
    xase
    0.53
    escent
    0.52
    MockMvc
    0.52
     createSlice
    0.52
     SqlParameter
    0.51
    Vidite
    0.50
     IBOutlet
    0.50
    Act Density 15.662%

    No Known Activations