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

    Neuronpedia

    INDEX
    Explanations

    phrases related to how things are evolving or playing out

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.75
    adaptiveStyles
    -0.70
     GenerationType
    -0.64
     ModelExpression
    -0.60
     iNdEx
    -0.60
    BeginContext
    -0.60
     picioare
    -0.58
    stdc
    -0.57
     nonatomic
    -0.57
    Datuak
    -0.57
    POSITIVE LOGITS
    TacToe
    0.46
    umman
    0.46
    rzej
    0.45
    UMIN
    0.44
    estacks
    0.41
    edict
    0.41
    ingway
    0.41
    Footnotes
    0.40
    chilas
    0.40
     zus
    0.40
    Act Density 1.844%

    No Known Activations