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

    Neuronpedia

    INDEX
    Explanations

    Object.keys, Object.assign, Object.values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SME
    0.41
     DOB
    0.40
    เหน
    0.39
    Gew
    0.39
    ソー
    0.38
     SOC
    0.38
     Rooney
    0.37
    আপ
    0.37
    Го
    0.37
    sockfd
    0.36
    POSITIVE LOGITS
     freeze
    0.57
     freezes
    0.50
    ifying
    0.49
    freeze
    0.49
     Freeze
    0.47
    ifiers
    0.46
     froze
    0.45
    assign
    0.45
     Object
    0.44
     Vật
    0.44
    Act Density 0.009%

    No Known Activations